diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..b55a960c56845bea0a778f8b2ab38f5fb4aa9e5a --- /dev/null +++ b/.gitignore @@ -0,0 +1,162 @@ +# https://github.com/github/gitignore/blob/main/Python.gitignore + +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +#pdm.lock +# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it +# in version control. +# https://pdm.fming.dev/#use-with-ide +.pdm.toml + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ \ No newline at end of file diff --git a/README.md b/README.md index bceab8ead53c598b8cc9d2b2e91731d1052f9ab1..52fba1831dd5ad2aef66ff762474b3a0665fcc61 100644 --- a/README.md +++ b/README.md @@ -1,92 +1,38 @@ -# nomad-app-aitoolkit - - +# nomad-app-notebook ## Getting started -To make it easy for you to get started with GitLab, here's a list of recommended next steps. - -Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)! - -## Add your files - -- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files -- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command: - -``` -cd existing_repo -git remote add origin https://gitlab.mpcdf.mpg.de/nomad-lab/apps/nomad-app-aitoolkit.git -git branch -M main -git push -uf origin main +Starting the appworker and the gui: +bash``` +export PYTHONPATH=$PWD/dependencies/apps/aitoolkit:$PYTHONPATH +export NOMAD_CONFIG=$PWD/dependencies/apps/aitoolkit/nomad.yaml +nomad admin run appworker ``` -## Integrate with your tools - -- [ ] [Set up project integrations](https://gitlab.mpcdf.mpg.de/nomad-lab/apps/nomad-app-aitoolkit/-/settings/integrations) - -## Collaborate with your team - -- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/) -- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html) -- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically) -- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/) -- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html) - -## Test and Deploy - -Use the built-in continuous integration in GitLab. - -- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html) -- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing(SAST)](https://docs.gitlab.com/ee/user/application_security/sast/) -- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html) -- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/) -- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html) - -*** - -# Editing this README - -When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thank you to [makeareadme.com](https://www.makeareadme.com/) for this template. - -## Suggestions for a good README -Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information. - -## Name -Choose a self-explaining name for your project. - -## Description -Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors. - -## Badges -On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge. - -## Visuals -Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method. - -## Installation -Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection. - -## Usage -Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README. - -## Support -Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc. - -## Roadmap -If you have ideas for releases in the future, it is a good idea to list them in the README. +bash``` +export NODE_OPTIONS=--openssl-legacy-provider +cd gui +yarn +yarn start +``` -## Contributing -State if you are open to contributions and what your requirements are for accepting them. +## TODO -For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self. +- [x] having notebook catergory +- [ ] parser for notebook files (if it is not exist yet) +- [ ] having the launch button +- [ ] having filter submenu +- [ ] defining common base class but hiding them from gui +- [ ] disable ai toolkit for oaisis users +- [ ] list categories doesn't show up (systems, methods) +- [ ] author list cannot be stored (notebook_authors, default_launch_url) +- [ ] search for list of authors +- [ ] datetime format +- [ ] is there any way to switch between schemas (Notebook > AI toolkit)? +- [ ] the nomad.yaml config part should be part of default for central deployments -You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser. -## Authors and acknowledgment -Show your appreciation to those who have contributed to the project. -## License -For open source projects, say how it is licensed. +/notebook_schema -## Project status -If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers. +/notebook_parser \ No newline at end of file diff --git a/ai_tootlkit_notebooks/PropaneOxidation.archive.json b/ai_tootlkit_notebooks/PropaneOxidation.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..00866a07aa94a01d9b311a94ad3cecb26aa23afe --- /dev/null +++ b/ai_tootlkit_notebooks/PropaneOxidation.archive.json @@ -0,0 +1,54 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Materials genes of heterogeneous catalysis from clean experiments and artificial intelligence", + "description": "This tutorial explores the application of SISSO to a consistent experimental data set in order to identify the key parameters correlated with the catalyst selectivity in propane oxidation.", + "date": "2022-6-23", + "notebook_path": "catalysis_MRS2021.ipynb", + "category": "advanced tutorial", + "systems": [ + "Heterogeneous catalysis" + ], + "methods": [ + "SISSO" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Foppa", + "first_name": "Lucas" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1557/s43577-021-00165-6" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/catalysis_MRS2021.ipynb" + }, + { + "kind": "article_url", + "url": "https://link.springer.com/article/10.1557/s43577-021-00165-6" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/PropaneOxidation" + } + ], + "related_publications": [ + { + "DOI_number": "10.1557/s43577-021-00165-6" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-atomic-features.archive.json b/ai_tootlkit_notebooks/analytics-atomic-features.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..4e8ab6970b1fa63e500dbe492a31aa60032c4c2f --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-atomic-features.archive.json @@ -0,0 +1,35 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Atomic-features-package usage demonstration", + "description": "In this tutorial, we show how the atomic-features-package can be accessed and used to explore the atomic features form various sources and to prepare the input features for machine-learning studies.", + "date": "2021-12-07", + "notebook_path": "atomic_features.ipynb", + "category": "query tutorial", + "systems": [ + "Atoms" + ], + "methods": [], + "platform": "Python", + "authors": [ + { + "last_name": "Naik", + "first_name": "Aakash A." + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/atomic_features.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-atomic-features" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-clustering-tutorial.archive.json b/ai_tootlkit_notebooks/analytics-clustering-tutorial.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..0a46290492162fd35f08f4691541cef6764b41f2 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-clustering-tutorial.archive.json @@ -0,0 +1,42 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to clustering", + "description": "In this tutorial, we introduce to the most popular clustering algorithms. We focus on partitioning, hierarchical and density-based clustering algorithms. The methods are tested on synthetic datasets of increasing complexity", + "date": "2021-01-21", + "notebook_path": "clustering_tutorial.ipynb", + "category": "beginner tutorial", + "systems": [ + "Synthetic data" + ], + "methods": [ + "Unsupervised learning", + "Clustering", + "k-means", + "Hierarchical clustering", + "DBSCAN", + "HDBSCAN" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/clustering_tutorial.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-clustering-tutorial" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-cmlkit.archive.json b/ai_tootlkit_notebooks/analytics-cmlkit.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..f1b1ee71f957fc25f8e5ef4a164a27ff4954a2fa --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-cmlkit.archive.json @@ -0,0 +1,51 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "cmlkit: Toolkit for Machine Learning in Materials Science and Quantum Chemistry", + "description": "In this tutorial, we will get to know cmlkit, a python package for specifying, evaluating, and optimising machine learning models, and use it to compete in the Nomad 2018 Kaggle challenge.", + "date": "2021-01-14", + "notebook_path": "cmlkit.ipynb", + "category": "advanced tutorial", + "systems": [ + "Transparent conducting oxides" + ], + "methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "SOAP", + "MBTR", + "Symmetry functions" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Langer", + "first_name": "Marcel F." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.48550/arXiv.2003.12081" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/cmlkit.ipynb" + }, + { + "kind": "article_url", + "url": "https://arxiv.org/pdf/2003.12081.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-cmlkit" + } + ], + "related_publications": [ + { + "DOI_number": "10.48550/arXiv.2003.12081" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-co2-sgd-tutorial.archive.json b/ai_tootlkit_notebooks/analytics-co2-sgd-tutorial.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..e9df4dede85e6cd1bf058a363ecfef2e17d1e46f --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-co2-sgd-tutorial.archive.json @@ -0,0 +1,65 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Subgroup discovery of catalysts\u2019 genes for carbon-dioxide activation on semiconductor oxides", + "description": "In this interactive tutorial we show the application of subgroup discovery for the search for indicators of carbond-dioxide activation with the aim of its further conversion.", + "date": "2021-08-26", + "notebook_path": "CO2_SGD.ipynb", + "category": "advanced tutorial", + "systems": [ + "CO2 activation", + "Heterogeneous catalysis", + "Semicondictor oxides" + ], + "methods": [ + "Subgroup discovery", + "Decision tree" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Mazheika", + "first_name": "Aliaksei" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Levchenko", + "first_name": "Sergey V." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.48550/arXiv.1912.06515" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/CO2_SGD.ipynb" + }, + { + "kind": "article_url", + "url": "https://arxiv.org/pdf/1912.06515" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-co2-sgd-tutorial" + } + ], + "related_publications": [ + { + "DOI_number": "10.48550/arXiv.1912.06515" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-compressed-sensing.archive.json b/ai_tootlkit_notebooks/analytics-compressed-sensing.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..f96f893d291c22260c04033242fb84ca11c4162f --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-compressed-sensing.archive.json @@ -0,0 +1,78 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Symbolic regression via compressed sensing: a tutorial", + "description": "In this tutorial we will show how to find descriptive parameters to predict materials properties using symbolic regrression combined with compressed sensing tools. The relative stability of the zincblende (ZB) versus rocksalt (RS) structure of binary materials is predicted and compared against a model trained with kernel ridge regression.", + "date": "2020-09-20", + "notebook_path": "compressed_sensing.ipynb", + "category": "beginner tutorial", + "systems": [ + "Octet binaries" + ], + "methods": [ + "Supervised learning", + "Regression", + "Compressed sensing", + "Symbolic regression", + "LASSO", + "SISSO", + "Kernel ridge regression", + "Features selection", + "Atomic features" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Ahmetcik", + "first_name": "Emre" + }, + { + "last_name": "Ziletti", + "first_name": "Angelo" + }, + { + "last_name": "Ouyang", + "first_name": "Runhai" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1088/1367-2630/aa57bf" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/compressed_sensing.ipynb" + }, + { + "kind": "article_url", + "url": "https://th.fhi-berlin.mpg.de/site/uploads/Publications/NJP-19-023017-2017.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-compressed-sensing" + }, + { + "kind": "video", + "url": "https://www.youtube.com/watch?v=73mLp6C2opY" + } + ], + "related_publications": [ + { + "DOI_number": "10.1088/1367-2630/aa57bf" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-convolutional-nn.archive.json b/ai_tootlkit_notebooks/analytics-convolutional-nn.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..cff5fe63772dc1d21b6487ee7097d0eb6f4ca2a9 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-convolutional-nn.archive.json @@ -0,0 +1,49 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to convolutional neural networks", + "description": "In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model with Keras, and explain the classification decision process using attentive response maps.", + "date": "2021-01-29", + "notebook_path": "convolutional_nn.ipynb", + "category": "intermediate tutorial", + "systems": [ + "Images" + ], + "methods": [ + "Supervised learning", + "Classification", + "Neural networks", + "Convolutional neural networks", + "Attentive response map" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Ziletti", + "first_name": "Angelo" + }, + { + "last_name": "Leitherer", + "first_name": "Andreas" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/convolutional_nn.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-convolutional-nn" + }, + { + "kind": "video", + "url": "https://youtu.be/MST8X1yCWK8" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-decision-tree.archive.json b/ai_tootlkit_notebooks/analytics-decision-tree.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..324dfe25548ca4bd037e3472138ca8d2ba29050a --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-decision-tree.archive.json @@ -0,0 +1,54 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to decision-trees methods", + "description": "In this tutorial we will introduce decision trees. We go through a toy model introducing the SKLearn API. We then discuss step by step the different theoretical aspects of trees. We then move to training a regression tree and classification tree on different datasets related to materials science. We end the tutorial by covering random forests and bagging classfiers.", + "date": "2020-12-08", + "notebook_path": "decision_tree.ipynb", + "category": "beginner tutorial", + "systems": [ + "Images", + "Metals", + "Insulators", + "matbench_expt_is_metal" + ], + "methods": [ + "Supervised learning", + "Regression", + "Classification", + "Decision tree", + "Random forest", + "Bagging classifier", + "Atomic features" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Speckhard", + "first_name": "Daniel" + }, + { + "last_name": "Leitherer", + "first_name": "Andreas" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/decision_tree.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-decision-tree" + }, + { + "kind": "video", + "url": "https://www.youtube.com/watch?v=YBy9STVaqvU" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-descriptor-role.archive.json b/ai_tootlkit_notebooks/analytics-descriptor-role.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..139beb1d5715f64d4c2fd2a0601303a4a33f38ae --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-descriptor-role.archive.json @@ -0,0 +1,68 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Predicting energy differences between crystal structures: (Meta-)stability of octet-binary compounds", + "description": "A tool for predicting the difference in the total energy between different polymorphs for 82 octet binary compounds, which gives an indication of the stability of the material. This is accomplished by identifying a set of descriptive parameters (a descriptor) from the free-atom data for the binary atomic species comprising the material using the Sure Independent Screening (SIS) + l0-norm minimization approach.", + "date": "2021-10-18", + "notebook_path": "descriptor_role.ipynb", + "category": "advanced tutorial", + "systems": [ + "Octet binaries", + "Rock salt", + "Zinc blende" + ], + "methods": [ + "Supervised learning", + "Regression", + "Features selection", + "SISSO", + "Atomic features" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Arif", + "first_name": "Mohammad-Yasin" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Purcell", + "first_name": "Thomas A. R." + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1103/PhysRevLett.114.105503" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/descriptor_role.ipynb" + }, + { + "kind": "article_url", + "url": "https://th.fhi.mpg.de/site/uploads/Publications/PRL-114-105503-2015.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-descriptor-role" + } + ], + "related_publications": [ + { + "DOI_number": "10.1103/PhysRevLett.114.105503" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-domain-of-applicability.archive.json b/ai_tootlkit_notebooks/analytics-domain-of-applicability.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..d1a5ad93bb49d43b464fe1a913533e6ac918ab25 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-domain-of-applicability.archive.json @@ -0,0 +1,60 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Identifying domains of applicability of machine-Learning models for materials science", + "description": "In this tutorial, we present a method, based on subgroup discovery, for detecting domains of applicability (DA) of ML models within a materials class. The domain of applicability of an ML model is the region of input space where the model predicts the target property with the smallest uncertainty. The utility of this approach is demonstrated by analyzing three state-of-the-art ML models for predicting the formation energy of transparent conducting oxides.", + "date": "2021-01-27", + "notebook_path": "domain_of_applicability.ipynb", + "category": "advanced tutorial", + "systems": [ + "Transparent conducting oxides" + ], + "methods": [ + "Supervised learning", + "Regression", + "Subgroup discovery", + "Kernel ridge regression", + "SOAP", + "MBTR", + "n-gram" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Arif", + "first_name": "Mohammad-Yasin" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1038/s41467-020-17112-9" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb" + }, + { + "kind": "article_url", + "url": " https://th.fhi-berlin.mpg.de/site/uploads/Publications/s41467-020-17112-9.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-domain-of-applicability" + } + ], + "related_publications": [ + { + "DOI_number": "10.1038/s41467-020-17112-9" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-dos-similarity-search.archive.json b/ai_tootlkit_notebooks/analytics-dos-similarity-search.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..20a7f4f72f793613e094082897e76eac47bd3f29 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-dos-similarity-search.archive.json @@ -0,0 +1,47 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Electronic density-of-states similarity search", + "description": "This notebook shows how to compute the similarity of materials in terms of their electronic density-of-states (DOS), from data retrieved from the NOMAD Archive.", + "date": "2022-3-30", + "notebook_path": "dos_similarity_search.ipynb", + "category": "intermediate tutorial", + "systems": [ + "Binaries", + "Ternaries" + ], + "methods": [ + "Similarity search", + "Fingerprint" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Gabaj", + "first_name": "\u0160imon" + }, + { + "last_name": "Kuban", + "first_name": "Martin" + }, + { + "last_name": "Rigamonti", + "first_name": "Santiago" + }, + { + "last_name": "Draxl", + "first_name": "Claudia" + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/dos_similarity_search.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-dos-similarity-search" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-error-estimates.archive.json b/ai_tootlkit_notebooks/analytics-error-estimates.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..663353ca51f621f701d85e0960ec46115408e130 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-error-estimates.archive.json @@ -0,0 +1,69 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Error estimates from high-accuracy electronic-structure reference calculations", + "description": "A set of tools to analyze the error in electronic structure calculations due to the choice of numerical settings. We use the NOMAD infrastructure to systematically investigate the deviances in total and relative energies as function of typical settings for basis sets, k-grids, etc. for 71 elemental and 81 binary solids in three different electronic-structure codes.", + "date": "2021-01-21", + "notebook_path": "error_estimates.ipynb", + "category": "advanced tutorial", + "systems": [ + "Binaries", + "Elemental solids" + ], + "methods": [ + "Supervised learning", + "Regression", + "Linear least-squares regression" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Bieniek", + "first_name": "Bj\u00f6rn" + }, + { + "last_name": "Strange", + "first_name": "Mikkel" + }, + { + "last_name": "Carbogno", + "first_name": "Christian" + }, + { + "last_name": "Arif", + "first_name": "Mohammad-Yasin" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.48550/arXiv.2008.10402" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/error_estimates.ipynb" + }, + { + "kind": "article_url", + "url": "https://th.fhi-berlin.mpg.de/site/uploads/Publications/2008.10402.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-error-estimates" + } + ], + "related_publications": [ + { + "DOI_number": "10.48550/arXiv.2008.10402" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-exploratory-analysis.archive.json b/ai_tootlkit_notebooks/analytics-exploratory-analysis.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..dcd3105ebe6f6e1b262e51f3b4a6d40147f0b4ac --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-exploratory-analysis.archive.json @@ -0,0 +1,50 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to exploratory analysis (unsupervised learning) of materials spaces", + "description": "Exploratory analyses make use of unsupervised learning techniques to extract information from unknown datasets. In this tutorial, we make use of some of the most popular clustering and dimension reduction algorithms to analyze a dataset composed of 82 octet-binary compounds.", + "date": "2021-02-04", + "notebook_path": "exploratory_analysis.ipynb", + "category": "beginner tutorial", + "systems": [ + "Octet binaries" + ], + "methods": [ + "Clustering", + "Dimensionality reduction", + "k-means", + "Hierarchical clustering", + "DBSCAN", + "HDBSCAN", + "DenPeak", + "PCA", + "t-SNE", + "MDS" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/exploratory_analysis.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-exploratory-analysis" + }, + { + "kind": "video", + "url": "https://www.youtube.com/watch?v=EJTjF9ehp7k" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-gap-si-surface.archive.json b/ai_tootlkit_notebooks/analytics-gap-si-surface.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..ea0aa2caef2481cd26a3e288c5a37c9e34b80ede --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-gap-si-surface.archive.json @@ -0,0 +1,55 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "The SOAP descriptor, Gaussian Approximation Potentials (GAP) and machine learning of force fields", + "description": "In this tutorial, we will be using a Gaussian Approximation Potentials to analyse results of TB DFT calculations on the Si surface. Along the way we will learn about different descriptors (2b, 3b, SOAP) to describe local atomic environment in order to predict energies and forces of the Si surface.", + "date": "2020-06-18", + "notebook_path": "gap_si_surface.ipynb", + "category": "intermediate tutorial", + "systems": [ + "Silicon", + "Surface" + ], + "methods": [ + "Supervised learning", + "Regression", + "Gaussian process regression", + "Kernel ridge regression", + "SOAP", + "Gaussian approximation potentials (GAP)" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Fekete", + "first_name": "\u00c1d\u00e1m" + }, + { + "last_name": "Stella", + "first_name": "Martina" + }, + { + "last_name": "Lambert", + "first_name": "Henry" + }, + { + "last_name": "De Vita", + "first_name": "Alessandro" + }, + { + "last_name": "Cs\u00e1nyi", + "first_name": "G\u00e1bor" + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/gap_si_surface.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-gap-si-surface" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-grain-boundaries.archive.json b/ai_tootlkit_notebooks/analytics-grain-boundaries.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..dba57f38a36077f59fa48736de831f383f84f8c6 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-grain-boundaries.archive.json @@ -0,0 +1,68 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Structure similarity and structure-property relationship: grain boundaries of alpha-Fe", + "description": "In this tutorial, we will be using a machine-learning method (clustering) to analyse results of grain-boundary (GB) calculations of alpha-iron. Along the way, we will learn about different methods to describe local atomic environment in order to calculate properties of GBs. We will use these properties to separate the different regions of the GB using clustering methods. Finally we will determine how the energy of the GB is changing according to the angle difference of the regions.", + "date": "2020-01-18", + "notebook_path": "grain_boundaries.ipynb", + "category": "advanced tutorial", + "systems": [ + "Iron", + "Grain boundaries" + ], + "methods": [ + "Unsupervised learning", + "Supervised learning", + "Clustering", + "Regression", + "k-means", + "Gaussian mixture" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Fekete", + "first_name": "\u00c1d\u00e1m" + }, + { + "last_name": "Stella", + "first_name": "Martina" + }, + { + "last_name": "Lambert", + "first_name": "Henry" + }, + { + "last_name": "De Vita", + "first_name": "Alessandro" + }, + { + "last_name": "Cs\u00e1nyi", + "first_name": "G\u00e1bor" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1016/j.cpc.2018.04.029" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/grain_boundaries.ipynb" + }, + { + "kind": "article_url", + "url": "https://www.sciencedirect.com/science/article/pii/S0010465518301450?via%3Dihub" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-grain-boundaries" + } + ], + "related_publications": [ + { + "DOI_number": "10.1016/j.cpc.2018.04.029" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-hierarchical-sisso.archive.json b/ai_tootlkit_notebooks/analytics-hierarchical-sisso.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..1b1f4e6f9fb27ee9cc7c027bb0e2cd43b1fb3afa --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-hierarchical-sisso.archive.json @@ -0,0 +1,62 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Hierarchical symbolic regression for identifying key physical parameters correlated with materials properties", + "description": "In this notebook, we describe a hierarchical symbolic-regression approach for finding, based on data, analytical expressions relating materials properties to simpler physicochemical parameters associated with the underlying processes governing the properties.", + "date": "2022-8-3", + "notebook_path": "hierarchical_sisso.ipynb", + "category": "advanced tutorial", + "systems": [ + "Bulk properties" + ], + "methods": [ + "SISSO" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Foppa", + "first_name": "Lucas" + }, + { + "last_name": "Purcell", + "first_name": "Thomas A. R." + }, + { + "last_name": "Levchenko", + "first_name": "Sergey V." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1103/PhysRevLett.129.055301" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/hierarchical_sisso.ipynb" + }, + { + "kind": "article_url", + "url": "https://journals.aps.org/prl/pdf/10.1103/PhysRevLett.129.055301" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-hierarchical-sisso" + } + ], + "related_publications": [ + { + "DOI_number": "10.1103/PhysRevLett.129.055301" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-kaggle-competition.archive.json b/ai_tootlkit_notebooks/analytics-kaggle-competition.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..fcb000ac3503c713118dc8c11e16d3cca4c928b6 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-kaggle-competition.archive.json @@ -0,0 +1,79 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "2018 NOMAD-Kaggle research competition", + "description": "In this tutorial, we will explore the best results of the NOMAD 2018 Kaggle research competition. The goal of this competition was to develop machine-learning models for the prediction of two target properties: the formation energy and the bandgap energy of transparent semiconducting oxides. The purpose of the modelling is to facilitate the discovery of new such materials and allow for advancements in (opto)electronic technologies", + "date": "2021-01-19", + "notebook_path": "kaggle_competition.ipynb", + "category": "advanced tutorial", + "systems": [ + "Transparent conducting oxides" + ], + "methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "Neural networks", + "SOAP", + "n-gram" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Liu", + "first_name": "Xiangyue" + }, + { + "last_name": "Sutton", + "first_name": "Christopher" + }, + { + "last_name": "Yamamoto", + "first_name": "Takenori" + }, + { + "last_name": "Blumenthal", + "first_name": "Lars" + }, + { + "last_name": "Golebiowski", + "first_name": "Jacek" + }, + { + "last_name": "Ziletti", + "first_name": "Angelo" + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1038/s41524-019-0239-3" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kaggle_competition.ipynb" + }, + { + "kind": "article_url", + "url": "https://th.fhi.mpg.de/site/uploads/Publications/s41524-019-0239-3.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kaggle-competition" + } + ], + "related_publications": [ + { + "DOI_number": "10.1038/s41524-019-0239-3" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-kappa_L_learning.archive.json b/ai_tootlkit_notebooks/analytics-kappa_L_learning.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..e6c31321c58f7a4453d3ac052cd6a55c5a601de6 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-kappa_L_learning.archive.json @@ -0,0 +1,46 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Accelerated Materials Exploration via AI-Generated Maps", + "description": "Notebook recreating the results of the paper by the same title and authors.", + "date": "2022-06-17", + "notebook_path": "kappa_screening_sisso.ipynb", + "category": "thermal transport", + "systems": [ + "Solid State Crystals" + ], + "methods": [ + "SISSO", + "Sensitivy Analysis" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Purcell", + "first_name": "Thomas A. R." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Carbogno", + "first_name": "Christian" + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kappa_screening_sisso.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kappa_L_learning" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-krr4mat.archive.json b/ai_tootlkit_notebooks/analytics-krr4mat.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..c9557a83ef63fb45ee1b65db4638f09143c2f5d3 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-krr4mat.archive.json @@ -0,0 +1,40 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to kernel ridge regression for materials-property prediction", + "description": "In this tutorial, we will explore the application of kernel ridge regression to the prediction of materials properties. We will begin with a largely informal, pragmatic introduction to kernel ridge regression, including a rudimentary implementation, in order to become familiar with the basic terminology and considerations. We will then discuss representations, and re-trace the NOMAD 2018 Kaggle challenge.", + "date": "2020-12-15", + "notebook_path": "krr4mat.ipynb", + "category": "beginner tutorial", + "systems": [ + "Transparent conducting oxides" + ], + "methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "SOAP" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Langer", + "first_name": "Marcel F." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/krr4mat.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-krr4mat" + }, + { + "kind": "video", + "url": "https://www.youtube.com/watch?v=H_MVlljpYHw" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-metalinsulator-prm2018.archive.json b/ai_tootlkit_notebooks/analytics-metalinsulator-prm2018.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..5520269cce1059e65f66b3b048a4792905b9b8f3 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-metalinsulator-prm2018.archive.json @@ -0,0 +1,55 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Predicting the metal-insulator classification of elements and binary systems", + "description": "This tutorial shows how to find descriptive parameters (short formulas) for the classification of materials properties. As an example, we address the classification of elemental and binary systems Ax\u200b\u200bBy\u200b\u200b into metals and non metals using experimental data extracted from the SpringerMaterials data base. The method is based on the algorithm sure independence screening and sparsifying operator (SISSO), which enables to search for optimal descriptors by scanning huge feature spaces. ", + "date": "2021-12-1", + "notebook_path": "", + "category": "advanced tutorial", + "systems": [ + "Binaries", + "Elements" + ], + "methods": [ + "SISSO", + "Classification" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Naik", + "first_name": "Aakash A." + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ahmetcik", + "first_name": "Emre" + }, + { + "last_name": "Ziletti", + "first_name": "Angelo" + }, + { + "last_name": "Ouyang", + "first_name": "Runhai" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-metalinsulator-prm2018" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-perovskite-tolerance-factor.archive.json b/ai_tootlkit_notebooks/analytics-perovskite-tolerance-factor.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..34f31b87017d0aff4220e4e47298caedc60515cb --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-perovskite-tolerance-factor.archive.json @@ -0,0 +1,73 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Finding a tolerance factor to predict perovskite stability with SISSO", + "description": "This tutorial shows how a tolerance factor for predicting perovskite stability can be learned from data with the sure-independece-screening-and-sparsifying-operator (SISSO) descriptor-identification approach.", + "date": "2022-05-18", + "notebook_path": "perovskites_tolerance_factor.ipynb", + "category": "advanced tutorial", + "systems": [ + "Perovskite" + ], + "methods": [ + "Supervised learning", + "Classification", + "Symbolic regression", + "Compressed sensing", + "SISSO", + "Decision tree", + "Features selection", + "Atomic features" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Foppa", + "first_name": "Lucas" + }, + { + "last_name": "Hassanzada", + "first_name": "Qaem" + }, + { + "last_name": "Bartel", + "first_name": "Christopher" + }, + { + "last_name": "Purcell", + "first_name": "Thomas A. R." + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1126/sciadv.aav0693" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/perovskites_tolerance_factor.ipynb" + }, + { + "kind": "article_url", + "url": "https://advances.sciencemag.org/content/advances/5/2/eaav0693.full.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-perovskite-tolerance-factor" + } + ], + "related_publications": [ + { + "DOI_number": "10.1126/sciadv.aav0693" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-query-nomad-archive.archive.json b/ai_tootlkit_notebooks/analytics-query-nomad-archive.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..e3d30db9aa0e65aaed315241440955ceb8356f5b --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-query-nomad-archive.archive.json @@ -0,0 +1,46 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Querying the NOMAD Archive and performing artificial-intelligence modeling", + "description": "In this tutorial, we demonstrate how to query the NOMAD Archive from the NOMAD Analytics toolkit. We then show examples of machine learning analysis performed on the retrieved data set.", + "date": "2021-04-14", + "notebook_path": "query_nomad_archive.ipynb", + "category": "query tutorial", + "systems": [ + "Ternaries" + ], + "methods": [ + "Unsupervised learning", + "Supervised learning", + "Regression", + "Clustering", + "Dimensionality reduction", + "Random forest" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/query_nomad_archive.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-query-nomad-archive" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-sgd-alloys-oxygen-reduction-evolution.archive.json b/ai_tootlkit_notebooks/analytics-sgd-alloys-oxygen-reduction-evolution.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..076981d07e9caebbfae91626ab9f1b20ed5e9b52 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-sgd-alloys-oxygen-reduction-evolution.archive.json @@ -0,0 +1,54 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to subgroup discovery: Identifying outstanding transition-metal-alloy catalysts", + "description": "This tutorial introduces, by means of two applications in materials science, the artificial-intelligence technique subgroup discovery.", + "date": "2021-10-28", + "notebook_path": "sgd_alloys_oxygen_reduction_evolution.ipynb", + "category": "intermediate tutorial", + "systems": [ + "Heterogeneous catalysis", + "Oxygen evolution reaction", + "Oxygen reduction reaction", + "Scaling relations" + ], + "methods": [ + "Subgroup discovery", + "Decision tree" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Foppa", + "first_name": "Lucas" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1007/s11244-021-01502-4" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_alloys_oxygen_reduction_evolution.ipynb" + }, + { + "kind": "article_url", + "url": "https://link.springer.com/content/pdf/10.1007/s11244-021-01502-4.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-alloys-oxygen-reduction-evolution" + } + ], + "related_publications": [ + { + "DOI_number": "10.1007/s11244-021-01502-4" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-sgd-propylene-oxidation-hte.archive.json b/ai_tootlkit_notebooks/analytics-sgd-propylene-oxidation-hte.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..f56fe9627265b2f1ffe3b359fda1a42182d6da78 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-sgd-propylene-oxidation-hte.archive.json @@ -0,0 +1,54 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Learning Design Rules for Catalysts from High-Throughput Experimentation and Theory via Subgroup Discovery", + "description": "This tutorial explores the application of subgroup discovery (SGD) to an experimental-theoretical data set in order to identify rules on key physicochemical parameters that describe the materials and environmental conditions associated with outstanding performance in heterogeneous catalysis.", + "date": "2022-2-09", + "notebook_path": "sgd_propylene_oxidation_hte.ipynb", + "category": "advanced tutorial", + "systems": [ + "Heterogeneous catalysis" + ], + "methods": [ + "Subgroup discovery" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Foppa", + "first_name": "Lucas" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1021/acscatal.1c04793" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_propylene_oxidation_hte.ipynb" + }, + { + "kind": "article_url", + "url": "https://pubs.acs.org/doi/10.1021/acscatal.1c04793" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-propylene-oxidation-hte" + } + ], + "related_publications": [ + { + "DOI_number": "10.1021/acscatal.1c04793" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-soap-atomic-charges.archive.json b/ai_tootlkit_notebooks/analytics-soap-atomic-charges.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..50afa26a4ac880df677a940555e894b33c359e4b --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-soap-atomic-charges.archive.json @@ -0,0 +1,42 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Machine learning atomic charges", + "description": "In this tutorial, we will use Gaussian process regression, GPR (or equivalently, Kernel Ridge Regression, KRR) to train and predict charges on atoms in small organic molecules.", + "date": "2019-09-26", + "notebook_path": "soap_atomic_charges.ipynb", + "category": "intermediate tutorial", + "systems": [ + "GDB molecular database", + "GDB7" + ], + "methods": [ + "Supervised learning", + "Regression", + "Gaussian process regression", + "Kernel ridge regression", + "SOAP" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Cs\u00e1nyi", + "first_name": "G\u00e1bor" + }, + { + "last_name": "Kermode", + "first_name": "James R." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/soap_atomic_charges.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-soap-atomic-charges" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-svm_classification.archive.json b/ai_tootlkit_notebooks/analytics-svm_classification.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..84113a59240d32b1dbd9a6c38720c6bd0d393bef --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-svm_classification.archive.json @@ -0,0 +1,37 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "An introduction to support-vector machine for classification", + "description": "In this tutorial...", + "date": "2022-03-31", + "notebook_path": "svm_classification.ipynb", + "category": "beginner tutorial", + "systems": [ + "Perovskite" + ], + "methods": [ + "SVM" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Hassanzada", + "first_name": "Qaem" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/svm_classification.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-svm_classification" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-tcmi.archive.json b/ai_tootlkit_notebooks/analytics-tcmi.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..c776e5bdc8f24f3daaadad4005e0d1d4143be003 --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-tcmi.archive.json @@ -0,0 +1,63 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to total cumulative mutual information", + "description": "This interactive notebook introduces the concepts and original implementation of total cumulative mutual information (TCMI), as presented in the related publication. The main results of the publication are also reproduced in a hands-on style", + "date": "2020-02-06", + "notebook_path": "tcmi.ipynb", + "category": "advanced tutorial", + "systems": [ + "Synthetic data", + "UCI regression dataset", + "Octet binaries" + ], + "methods": [ + "Supervised learning", + "Unsupervised learning", + "Features selection", + "Information theory", + "Mutual information", + "Cumulative entropy", + "Clustering", + "TCMI" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Regler", + "first_name": "Benjamin" + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.48550/arXiv.2001.11212" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tcmi.ipynb" + }, + { + "kind": "article_url", + "url": "https://arxiv.org/pdf/2001.11212" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tcmi" + } + ], + "related_publications": [ + { + "DOI_number": "10.48550/arXiv.2001.11212" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-tetradymite-PRM2020.archive.json b/ai_tootlkit_notebooks/analytics-tetradymite-PRM2020.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..2df2fa19164404c8ee07555f9b98e97747ea8b9a --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-tetradymite-PRM2020.archive.json @@ -0,0 +1,64 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Discovery of new topological insulators in alloyed tetradymites", + "description": "Learn how to find descriptive parameters (short formulas) that predict whether alloyed materials are topological or trivial insulators, using the example of tetradymites. This notebook is based on the algorithm 'sure independence screening and sparsifying operator' (SISSO) that enables to search for optimal descriptor by scanning huge feature spaces.", + "date": "2020-09-15", + "notebook_path": "tetradymite_PRM2020.ipynb", + "category": "advanced tutorial", + "systems": [ + "Tetradymites", + "Topological insulators" + ], + "methods": [ + "Supervised learning", + "Classification", + "Symbolic regression", + "Features selection", + "Atomic features", + "SISSO" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Purcell", + "first_name": "Thomas A. R." + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + }, + { + "last_name": "Scheffler", + "first_name": "Matthias" + } + ], + "references": [ + { + "kind": "article_doi", + "url": "https://doi.org/10.1103/PhysRevMaterials.4.034204" + }, + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tetradymite_PRM2020.ipynb" + }, + { + "kind": "article_url", + "url": "https://th.fhi.mpg.de/site/uploads/Publications/PhysRevMaterials.4.034204.pdf" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tetradymite-PRM2020" + } + ], + "related_publications": [ + { + "DOI_number": "10.1103/PhysRevMaterials.4.034204" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/analytics-tutorial-template.archive.json b/ai_tootlkit_notebooks/analytics-tutorial-template.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..5019c440dc2c415dcf492e92f394ef1ffec7b2bc --- /dev/null +++ b/ai_tootlkit_notebooks/analytics-tutorial-template.archive.json @@ -0,0 +1,50 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Introduction to multilayer perceptrons (deep neural networks)", + "description": "In this tutorial, we discuss how multilayer perceptrons, a standard neural-network architecture, can be employed for regression tasks. Specifically, we will use the ElemNet neural-network architecture to predict the volume per atom of inorganic compounds, where the Open Quantum Materials Database (OQMD) is used as a resource.", + "date": "2021-01-29", + "notebook_path": "nn_regression.ipynb", + "category": "beginner tutorial", + "systems": [ + "Inorganic compounds", + "OQMD database" + ], + "methods": [ + "Supervised learning", + "Regression", + "Neural networks", + "Deep neural networks", + "Atomic features" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Leitherer", + "first_name": "Andreas" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + }, + { + "last_name": "Ghiringhelli", + "first_name": "Luca M." + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/nn_regression.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template" + }, + { + "kind": "video", + "url": "https://www.youtube.com/watch?v=U0lI5n8Hleo" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/proto_archetype_clustering_sisso.archive.json b/ai_tootlkit_notebooks/proto_archetype_clustering_sisso.archive.json new file mode 100644 index 0000000000000000000000000000000000000000..fba2d8a5a371ca13615eac65ebfe7d0a73026c55 --- /dev/null +++ b/ai_tootlkit_notebooks/proto_archetype_clustering_sisso.archive.json @@ -0,0 +1,38 @@ +{ + "data": { + "m_def": "notebook_schema.schema.AIToolkitNotebook", + "name": "Proto- and Archetype Clustering-based SISSO", + "description": "In this tutorial two clustering methods, namely unsupervised k-means and supervised deep-aa, will be used to extract proto- and archetypes, respectively, along with corresponding clusters. The set of proto- or archetypes can be used as a substantially reduced training set for Single-Task SISSO, which outperforms random selection, while the corresponding clusters allow for an educated material2task-assignment of all training and test materials for Multi-Task SISSO, whose training on the whole training set outperforms corresponding training of Single-Task SISSO.", + "date": "2021-12-20", + "notebook_path": "proto_archetype_clustering_sisso.ipynb", + "category": "beginner tutorial", + "systems": [ + "System" + ], + "methods": [ + "Clustering", + "SISSO" + ], + "platform": "Python", + "authors": [ + { + "last_name": "Oehlers", + "first_name": "Milena" + }, + { + "last_name": "Sbail\u00f2", + "first_name": "Luigi" + } + ], + "references": [ + { + "kind": "hub", + "url": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/proto_archetype_clustering_sisso.ipynb" + }, + { + "kind": "repository", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/proto_archetype_clustering_sisso" + } + ] + } +} \ No newline at end of file diff --git a/ai_tootlkit_notebooks/tutorial_stats.ipynb b/ai_tootlkit_notebooks/tutorial_stats.ipynb new file mode 100644 index 0000000000000000000000000000000000000000..b533ffbeac62a0c382ea6a61b9b54018e62dd8ba --- /dev/null +++ b/ai_tootlkit_notebooks/tutorial_stats.ipynb @@ -0,0 +1,612 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 143, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[{'authors': ['Arif, Mohammad-Yasin', 'Sbailò, Luigi', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Identifying domains of applicability of machine-Learning models for materials science', 'description': 'In this tutorial, we present a method, based on subgroup discovery, for detecting domains of applicability (DA) of ML models within a materials class. The domain of applicability of an ML model is the region of input space where the model predicts the target property with the smallest uncertainty. The utility of this approach is demonstrated by analyzing three state-of-the-art ML models for predicting the formation energy of transparent conducting oxides.', 'notebook_name': 'domain_of_applicability.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-domain-of-applicability', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb', 'link_paper': ' https://th.fhi-berlin.mpg.de/site/uploads/Publications/s41467-020-17112-9.pdf', 'link_doi_paper': '10.1038/s41467-020-17112-9', 'updated': '2021-01-27', 'flags': {'featured': True, 'top_of_list': False, 'paper': True}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Transparent conducting oxides'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Subgroup discovery', 'Kernel ridge regression', 'SOAP', 'MBTR', 'n-gram'], 'platform': ['jupyter']}}, {'authors': ['Langer, Marcel F.'], 'email': 'langer@fhi-berlin.mpg.de', 'title': 'cmlkit: Toolkit for Machine Learning in Materials Science and Quantum Chemistry', 'description': 'In this tutorial, we will get to know cmlkit, a python package for specifying, evaluating, and optimising machine learning models, and use it to compete in the Nomad 2018 Kaggle challenge.', 'notebook_name': 'cmlkit.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-cmlkit', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/cmlkit.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/cmlkit.ipynb', 'link_paper': 'https://arxiv.org/pdf/2003.12081.pdf', 'link_doi_paper': '10.48550/arXiv.2003.12081', 'updated': '2021-01-14', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Transparent conducting oxides'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Kernel ridge regression', 'SOAP', 'MBTR', 'Symmetry functions'], 'platform': ['jupyter']}}, {'authors': ['Foppa, Lucas', 'Hassanzada, Qaem', 'Bartel, Christopher', 'Purcell, Thomas A. R.', 'Sbailò, Luigi', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Finding a tolerance factor to predict perovskite stability with SISSO', 'description': 'This tutorial shows how a tolerance factor for predicting perovskite stability can be learned from data with the sure-independece-screening-and-sparsifying-operator (SISSO) descriptor-identification approach.', 'notebook_name': 'perovskites_tolerance_factor.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-perovskite-tolerance-factor', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/perovskites_tolerance_factor.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/perovskites_tolerance_factor.ipynb', 'link_paper': 'https://advances.sciencemag.org/content/advances/5/2/eaav0693.full.pdf', 'link_doi_paper': '10.1126/sciadv.aav0693', 'updated': '2022-05-18', 'flags': {'featured': True, 'top_of_list': False, 'paper': True}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'category': ['advanced tutorial'], 'application_system': ['Perovskite'], 'ai_methods': ['Supervised learning', 'Classification', 'Symbolic regression', 'Compressed sensing', 'SISSO', 'Decision tree', 'Features selection', 'Atomic features'], 'platform': ['jupyter']}}, {'authors': ['Ahmetcik, Emre', 'Ziletti, Angelo', 'Ouyang, Runhai', 'Sbailò, Luigi', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Symbolic regression via compressed sensing: a tutorial', 'description': 'In this tutorial we will show how to find descriptive parameters to predict materials properties using symbolic regrression combined with compressed sensing tools. The relative stability of the zincblende (ZB) versus rocksalt (RS) structure of binary materials is predicted and compared against a model trained with kernel ridge regression.', 'notebook_name': 'compressed_sensing.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-compressed-sensing', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/compressed_sensing.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/compressed_sensing.ipynb', 'link_video': 'https://www.youtube.com/watch?v=73mLp6C2opY', 'link_paper': 'https://th.fhi-berlin.mpg.de/site/uploads/Publications/NJP-19-023017-2017.pdf', 'link_doi_paper': '10.1088/1367-2630/aa57bf', 'updated': '2020-09-20', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_keyword': [], 'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Octet binaries'], 'category': ['beginner tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Compressed sensing', 'Symbolic regression', 'LASSO', 'SISSO', 'Kernel ridge regression', 'Features selection', 'Atomic features'], 'platform': ['jupyter']}}, {'authors': ['Sbailò, Luigi', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Querying the NOMAD Archive and performing artificial-intelligence modeling', 'description': 'In this tutorial, we demonstrate how to query the NOMAD Archive from the NOMAD Analytics toolkit. We then show examples of machine learning analysis performed on the retrieved data set.', 'notebook_name': 'query_nomad_archive.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-query-nomad-archive', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/query_nomad_archive.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/query_nomad_archive.ipynb', 'updated': '2021-04-14', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Analysing the content of the Archive'], 'application_system': ['Ternaries'], 'category': ['query tutorial'], 'ai_methods': ['Unsupervised learning', 'Supervised learning', 'Regression', 'Clustering', 'Dimensionality reduction', 'Random forest'], 'platform': ['jupyter']}}, {'authors': ['Speckhard, Daniel', 'Leitherer, Andreas', 'Ghiringhelli, Luca M.'], 'email': 'speckhard@fhi-berlin.mpg.de', 'title': 'Introduction to decision-trees methods', 'description': 'In this tutorial we will introduce decision trees. We go through a toy model introducing the SKLearn API. We then discuss step by step the different theoretical aspects of trees. We then move to training a regression tree and classification tree on different datasets related to materials science. We end the tutorial by covering random forests and bagging classfiers.', 'notebook_name': 'decision_tree.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-decision-tree', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/decision_tree.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/decision_tree.ipynb', 'link_video': 'https://www.youtube.com/watch?v=YBy9STVaqvU', 'updated': '2020-12-08', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Images', 'Metals', 'Insulators', 'matbench_expt_is_metal'], 'category': ['beginner tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Classification', 'Decision tree', 'Random forest', 'Bagging classifier', 'Atomic features'], 'platform': ['jupyter']}}, {'authors': ['Sbailò, Luigi', 'Ghiringhelli, Luca M.'], 'email': 'sbailo@fhi-berlin.mpg.de', 'title': 'Introduction to exploratory analysis (unsupervised learning) of materials spaces', 'description': 'Exploratory analyses make use of unsupervised learning techniques to extract information from unknown datasets. In this tutorial, we make use of some of the most popular clustering and dimension reduction algorithms to analyze a dataset composed of 82 octet-binary compounds.', 'notebook_name': 'exploratory_analysis.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-exploratory-analysis', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/exploratory_analysis.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/exploratory_analysis.ipynb', 'link_video': 'https://www.youtube.com/watch?v=EJTjF9ehp7k', 'updated': '2021-02-04', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Octet binaries'], 'category': ['beginner tutorial'], 'ai_methods': ['Clustering', 'Dimensionality reduction', 'k-means', 'Hierarchical clustering', 'DBSCAN', 'HDBSCAN', 'DenPeak', 'PCA', 't-SNE', 'MDS'], 'platform': ['jupyter']}}, {'authors': ['Leitherer, Andreas', 'Ziletti, Angelo', 'Ghiringhelli, Luca M.'], 'email': 'leitherer@fhi-berlin.mpg.de', 'title': 'ARISE - Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning', 'description': 'In this tutorial, we give an introduction to ARISE (ARtificial-Intelligence-based Structure Evaluation), a powerful Bayesian-deep-neural-network tool for the recognition of atomistic structures (A. Leitherer, A. Ziletti, and L.M. Ghiringhelli, Nat. Commun. 12, 6234, 2021). ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates. By applying unsupervised learning to the internal neural-network representations, one can reveal grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties.', 'notebook_name': 'ARISE.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/ARISE.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/ARISE.ipynb', 'link_paper': 'https://www.nature.com/articles/s41467-021-26511-5.pdf', 'link_doi_paper': '10.1038/s41467-021-26511-5', 'updated': '2021-03-22', 'flags': {'featured': True, 'top_of_list': False, 'paper': True}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Grain boundaries', 'Binaries', 'Ternaries', 'Low-dimensional materials'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Neural networks', 'Bayesian deep learning', 'Unsupervised learning', 'Clustering', 'Dimensionality reduction', 'HDBSCAN', 'UMAP', 'SOAP'], 'platform': ['jupyter']}}, {'authors': ['Fekete, Ádám', 'Stella, Martina', 'Lambert, Henry', 'De Vita, Alessandro', 'Csányi, Gábor'], 'email': 'adam.fekete@kcl.ac.uk', 'title': 'The SOAP descriptor, Gaussian Approximation Potentials (GAP) and machine learning of force fields', 'description': 'In this tutorial, we will be using a Gaussian Approximation Potentials to analyse results of TB DFT calculations on the Si surface. Along the way we will learn about different descriptors (2b, 3b, SOAP) to describe local atomic environment in order to predict energies and forces of the Si surface.', 'notebook_name': 'gap_si_surface.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-gap-si-surface', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/gap_si_surface.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/gap_si_surface.ipynb', 'updated': '2020-06-18', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Silicon', 'Surface'], 'category': ['intermediate tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Gaussian process regression', 'Kernel ridge regression', 'SOAP', 'Gaussian approximation potentials (GAP)'], 'platform': ['jupyter']}}, {'authors': ['Hassanzada, Qaem', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'An introduction to support-vector machine for classification', 'description': 'In this tutorial...', 'notebook_name': 'svm_classification.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-svm_classification', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/svm_classification.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/svm_classification.ipynb', 'updated': '2022-03-31', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_keyword': ['SVM'], 'application_section': ['Materials property prediction'], 'application_system': ['Perovskite'], 'category': ['beginner tutorial'], 'ai_methods': ['SVM'], 'platform': ['jupyter']}}, {'authors': ['Mazheika, Aliaksei', 'Sbailò, Luigi', 'Ghiringhelli, Luca M.', 'Levchenko, Sergey V.', 'Scheffler, Matthias'], 'email': 'mazheika@fhi-berlin.mpg.de', 'title': 'Subgroup discovery of catalysts’ genes for carbon-dioxide activation on semiconductor oxides', 'description': 'In this interactive tutorial we show the application of subgroup discovery for the search for indicators of carbond-dioxide activation with the aim of its further conversion.', 'notebook_name': 'CO2_SGD.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-co2-sgd-tutorial', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/CO2_SGD.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/CO2_SGD.ipynb', 'link_paper': 'https://arxiv.org/pdf/1912.06515', 'link_doi_paper': '10.48550/arXiv.1912.06515', 'updated': '2021-08-26', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['CO2 activation', 'Heterogeneous catalysis', 'Semicondictor oxides'], 'category': ['advanced tutorial'], 'ai_methods': ['Subgroup discovery', 'Decision tree'], 'platform': ['jupyter']}}, {'authors': ['Foppa, Lucas', 'Ghiringhelli, Luca M.', 'Scheffler, Matthias'], 'email': 'foppa@fhi-berlin.mpg.de', 'title': 'Learning Design Rules for Catalysts from High-Throughput Experimentation and Theory via Subgroup Discovery', 'description': 'This tutorial explores the application of subgroup discovery (SGD) to an experimental-theoretical data set in order to identify rules on key physicochemical parameters that describe the materials and environmental conditions associated with outstanding performance in heterogeneous catalysis.', 'notebook_name': 'sgd_propylene_oxidation_hte.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-propylene-oxidation-hte', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_propylene_oxidation_hte.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/sgd_propylene_oxidation_hte.ipynb', 'link_paper': 'https://pubs.acs.org/doi/10.1021/acscatal.1c04793', 'link_doi_paper': '10.1021/acscatal.1c04793', 'updated': '2022-2-09', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Heterogeneous catalysis'], 'category': ['advanced tutorial'], 'ai_methods': ['Subgroup discovery'], 'platform': ['jupyter']}}, {'authors': ['Liu, Xiangyue', 'Sutton, Christopher', 'Yamamoto, Takenori', 'Blumenthal, Lars', 'Golebiowski, Jacek', 'Ziletti, Angelo', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': '2018 NOMAD-Kaggle research competition', 'description': 'In this tutorial, we will explore the best results of the NOMAD 2018 Kaggle research competition. The goal of this competition was to develop machine-learning models for the prediction of two target properties: the formation energy and the bandgap energy of transparent semiconducting oxides. The purpose of the modelling is to facilitate the discovery of new such materials and allow for advancements in (opto)electronic technologies', 'notebook_name': 'kaggle_competition.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kaggle-competition', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kaggle_competition.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/kaggle_competition.ipynb', 'link_paper': 'https://th.fhi.mpg.de/site/uploads/Publications/s41524-019-0239-3.pdf', 'link_doi_paper': '10.1038/s41524-019-0239-3', 'updated': '2021-01-19', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Transparent conducting oxides'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Kernel ridge regression', 'Neural networks', 'SOAP', 'n-gram'], 'platform': ['jupyter']}}, {'authors': ['Naik ,Aakash A.', 'Sbailò, Luigi', 'Ahmetcik, Emre', 'Ziletti, Angelo', 'Ouyang, Runhai', 'Ghiringhelli, Luca M.', 'Scheffler, Matthias'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Predicting the metal-insulator classification of elements and binary systems', 'description': 'This tutorial shows how to find descriptive parameters (short formulas) for the classification of materials properties. As an example, we address the classification of elemental and binary systems Ax\\u200b\\u200bBy\\u200b\\u200b into metals and non metals using experimental data extracted from the SpringerMaterials data base. The method is based on the algorithm sure independence screening and sparsifying operator (SISSO), which enables to search for optimal descriptors by scanning huge feature spaces. ', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-metalinsulator-prm2018', 'link': '', 'link_public': '', 'updated': '2021-12-1', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Binaries', 'Elements'], 'category': ['advanced tutorial'], 'ai_methods': ['SISSO', 'Classification'], 'platform': ['jupyter']}}, {'authors': ['Ziletti, Angelo', 'Leitherer, Andreas', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Introduction to convolutional neural networks', 'description': 'In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model with Keras, and explain the classification decision process using attentive response maps.', 'notebook_name': 'convolutional_nn.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-convolutional-nn', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/convolutional_nn.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/convolutional_nn.ipynb', 'link_video': 'https://youtu.be/MST8X1yCWK8', 'updated': '2021-01-29', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Images'], 'category': ['intermediate tutorial'], 'ai_methods': ['Supervised learning', 'Classification', 'Neural networks', 'Convolutional neural networks', 'Attentive response map'], 'platform': ['jupyter']}}, {'authors': ['Foppa, Lucas', 'Purcell, Thomas A. R.', 'Levchenko, Sergey V.', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.'], 'email': 'foppa@fhi-berlin.mpg.de', 'title': 'Hierarchical symbolic regression for identifying key physical parameters correlated with materials properties', 'description': 'In this notebook, we describe a hierarchical symbolic-regression approach for finding, based on data, analytical expressions relating materials properties to simpler physicochemical parameters associated with the underlying processes governing the properties.', 'notebook_name': 'hierarchical_sisso.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-hierarchical-sisso', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/hierarchical_sisso.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/hierarchical_sisso.ipynb', 'link_paper': 'https://journals.aps.org/prl/pdf/10.1103/PhysRevLett.129.055301', 'link_doi_paper': '10.1103/PhysRevLett.129.055301', 'updated': '2022-8-3', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Bulk properties'], 'category': ['advanced tutorial'], 'ai_methods': ['SISSO'], 'platform': ['jupyter']}}, {'authors': ['Fekete, Ádám', 'Stella, Martina', 'Lambert, Henry', 'De Vita, Alessandro', 'Csányi, Gábor'], 'email': 'adam.fekete@kcl.ac.uk', 'title': 'Structure similarity and structure-property relationship: grain boundaries of alpha-Fe', 'description': 'In this tutorial, we will be using a machine-learning method (clustering) to analyse results of grain-boundary (GB) calculations of alpha-iron. Along the way, we will learn about different methods to describe local atomic environment in order to calculate properties of GBs. We will use these properties to separate the different regions of the GB using clustering methods. Finally we will determine how the energy of the GB is changing according to the angle difference of the regions.', 'notebook_name': 'grain_boundaries.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-grain-boundaries', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/grain_boundaries.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/grain_boundaries.ipynb', 'link_paper': 'https://www.sciencedirect.com/science/article/pii/S0010465518301450?via%3Dihub', 'link_doi_paper': '10.1016/j.cpc.2018.04.029', 'updated': '2020-01-18', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Iron', 'Grain boundaries'], 'category': ['advanced tutorial'], 'ai_methods': ['Unsupervised learning', 'Supervised learning', 'Clustering', 'Regression', 'k-means', 'Gaussian mixture'], 'platform': ['jupyter']}}, {'authors': ['Foppa, Lucas', 'Ghiringhelli, Luca M.', 'Scheffler, Matthias'], 'email': 'foppa@fhi-berlin.mpg.de', 'title': 'Materials genes of heterogeneous catalysis from clean experiments and artificial intelligence', 'description': 'This tutorial explores the application of SISSO to a consistent experimental data set in order to identify the key parameters correlated with the catalyst selectivity in propane oxidation.', 'notebook_name': 'catalysis_MRS2021.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/PropaneOxidation', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/catalysis_MRS2021.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/catalysis_MRS2021.ipynb', 'link_paper': 'https://link.springer.com/article/10.1557/s43577-021-00165-6', 'link_doi_paper': '10.1557/s43577-021-00165-6', 'updated': '2022-6-23', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Heterogeneous catalysis'], 'category': ['advanced tutorial'], 'ai_methods': ['SISSO'], 'platform': ['jupyter']}}, {'authors': ['Naik ,Aakash A.', 'Ghiringhelli, Luca M.'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Atomic-features-package usage demonstration', 'description': 'In this tutorial, we show how the atomic-features-package can be accessed and used to explore the atomic features form various sources and to prepare the input features for machine-learning studies.', 'notebook_name': 'atomic_features.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-atomic-features', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/atomic_features.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/atomic_features.ipynb', 'updated': '2021-12-07', 'labels': {'application_system': ['Atoms'], 'category': ['query tutorial'], 'platform': ['jupyter'], 'ai_methods': []}}, {'authors': ['Regler, Benjamin', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.'], 'email': 'regler@fhi-berlin.mpg.de', 'title': 'Introduction to total cumulative mutual information', 'description': 'This interactive notebook introduces the concepts and original implementation of total cumulative mutual information (TCMI), as presented in the related publication. The main results of the publication are also reproduced in a hands-on style', 'notebook_name': 'tcmi.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tcmi', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tcmi.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/tcmi.ipynb', 'link_paper': 'https://arxiv.org/pdf/2001.11212', 'link_doi_paper': '10.48550/arXiv.2001.11212', 'updated': '2020-02-06', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Synthetic data', 'UCI regression dataset', 'Octet binaries'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Unsupervised learning', 'Features selection', 'Information theory', 'Mutual information', 'Cumulative entropy', 'Clustering', 'TCMI'], 'language': ['python'], 'platform': ['jupyter']}}, {'authors': ['Csányi, Gábor', 'Kermode, James R.'], 'email': 'gc121@cam.ac.uk', 'title': 'Machine learning atomic charges', 'description': 'In this tutorial, we will use Gaussian process regression, GPR (or equivalently, Kernel Ridge Regression, KRR) to train and predict charges on atoms in small organic molecules.', 'notebook_name': 'soap_atomic_charges.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-soap-atomic-charges', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/soap_atomic_charges.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/soap_atomic_charges.ipynb', 'updated': '2019-09-26', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['GDB molecular database', 'GDB7'], 'category': ['intermediate tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Gaussian process regression', 'Kernel ridge regression', 'SOAP'], 'platform': ['jupyter']}}, {'authors': ['Oehlers, Milena', 'Sbailò, Luigi'], 'email': 'milenaoehlers@gmail.com', 'title': 'Proto- and Archetype Clustering-based SISSO', 'description': 'In this tutorial two clustering methods, namely unsupervised k-means and supervised deep-aa, will be used to extract proto- and archetypes, respectively, along with corresponding clusters. The set of proto- or archetypes can be used as a substantially reduced training set for Single-Task SISSO, which outperforms random selection, while the corresponding clusters allow for an educated material2task-assignment of all training and test materials for Multi-Task SISSO, whose training on the whole training set outperforms corresponding training of Single-Task SISSO.', 'notebook_name': 'proto_archetype_clustering_sisso.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/proto_archetype_clustering_sisso', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/proto_archetype_clustering_sisso.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/proto_archetype_clustering_sisso.ipynb', 'updated': '2021-12-20', 'flags': {'featured': False, 'top_of_list': False}, 'labels': {'application_keyword': ['k-means', 'deep-aa', 'SISSO', 'sisso', 'archetypes', 'prototypes', 'clustering', 'training set reduction', 'multi-task', 'single-task', 'unsupervised', 'supervised'], 'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['System'], 'category': ['beginner tutorial'], 'ai_methods': ['Clustering', 'SISSO'], 'platform': ['jupyter']}}, {'authors': ['Leitherer, Andreas', 'Sbailò, Luigi', 'Ghiringhelli, Luca M.'], 'email': 'leitherer@fhi-berlin.mpg.de', 'title': 'Introduction to multilayer perceptrons (deep neural networks)', 'description': 'In this tutorial, we discuss how multilayer perceptrons, a standard neural-network architecture, can be employed for regression tasks. Specifically, we will use the ElemNet neural-network architecture to predict the volume per atom of inorganic compounds, where the Open Quantum Materials Database (OQMD) is used as a resource.', 'notebook_name': 'nn_regression.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/nn_regression.ipynb', 'link_public': 'https://nomad-lab.eu/prod/analytics/public/user-redirect/notebooks/tutorials/nn_regression.ipynb', 'link_video': 'https://www.youtube.com/watch?v=U0lI5n8Hleo', 'updated': '2021-01-29', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Materials property prediction'], 'application_system': ['Inorganic compounds', 'OQMD database'], 'category': ['beginner tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Neural networks', 'Deep neural networks', 'Atomic features'], 'platform': ['jupyter']}}, {'authors': ['Langer, Marcel F.'], 'email': 'langer@fhi-berlin.mpg.de', 'title': 'Introduction to kernel ridge regression for materials-property prediction', 'description': 'In this tutorial, we will explore the application of kernel ridge regression to the prediction of materials properties. We will begin with a largely informal, pragmatic introduction to kernel ridge regression, including a rudimentary implementation, in order to become familiar with the basic terminology and considerations. We will then discuss representations, and re-trace the NOMAD 2018 Kaggle challenge.', 'notebook_name': 'krr4mat.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-krr4mat', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/krr4mat.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/krr4mat.ipynb', 'link_video': 'https://www.youtube.com/watch?v=H_MVlljpYHw', 'updated': '2020-12-15', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Transparent conducting oxides'], 'category': ['beginner tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Kernel ridge regression', 'SOAP'], 'platform': ['jupyter']}}, {'authors': ['Purcell, Thomas A. R.', 'Scheffler, Matthias', 'Ghiringhelli, Luca M.', 'Carbogno, Christian'], 'email': 'purcell@fhi-berlin.mpg.de', 'title': 'Accelerated Materials Exploration via AI-Generated Maps', 'description': 'Notebook recreating the results of the paper by the same title and authors.', 'notebook_name': 'kappa_screening_sisso.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kappa_L_learning', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kappa_screening_sisso.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/kappa_screening_sisso.ipynb', 'updated': '2022-06-17', 'flags': {'featured': True, 'top_of_list': False, 'paper': True}, 'labels': {'application_section': ['Thermal Conductivity'], 'application_system': ['Solid State Crystals'], 'category': ['thermal transport'], 'ai_methods': ['SISSO', 'Sensitivy Analysis'], 'platform': ['jupyter']}}, {'authors': ['Sbailò, Luigi', 'Ghiringhelli, Luca M.'], 'email': 'sbailo@fhi-berlin.mpg.de', 'title': 'Introduction to clustering', 'description': 'In this tutorial, we introduce to the most popular clustering algorithms. We focus on partitioning, hierarchical and density-based clustering algorithms. The methods are tested on synthetic datasets of increasing complexity', 'notebook_name': 'clustering_tutorial.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-clustering-tutorial', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/clustering_tutorial.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/clustering_tutorial.ipynb', 'updated': '2021-01-21', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Synthetic data'], 'category': ['beginner tutorial'], 'ai_methods': ['Unsupervised learning', 'Clustering', 'k-means', 'Hierarchical clustering', 'DBSCAN', 'HDBSCAN'], 'platform': ['jupyter']}}, {'authors': ['Foppa, Lucas', 'Ghiringhelli, Luca M.'], 'email': 'foppa@fhi-berlin.mpg.de', 'title': 'Introduction to subgroup discovery: Identifying outstanding transition-metal-alloy catalysts', 'description': 'This tutorial introduces, by means of two applications in materials science, the artificial-intelligence technique subgroup discovery.', 'notebook_name': 'sgd_alloys_oxygen_reduction_evolution.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-alloys-oxygen-reduction-evolution', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_alloys_oxygen_reduction_evolution.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/sgd_alloys_oxygen_reduction_evolution.ipynb', 'link_paper': 'https://link.springer.com/content/pdf/10.1007/s11244-021-01502-4.pdf', 'link_doi_paper': '10.1007/s11244-021-01502-4', 'updated': '2021-10-28', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Heterogeneous catalysis', 'Oxygen evolution reaction', 'Oxygen reduction reaction', 'Scaling relations'], 'category': ['intermediate tutorial'], 'ai_methods': ['Subgroup discovery', 'Decision tree'], 'platform': ['jupyter']}}, {'authors': ['Gabaj, Šimon', 'Kuban, Martin', 'Rigamonti, Santiago', 'Draxl, Claudia'], 'email': 'gabajsim@physik.hu-berlin.de', 'title': 'Electronic density-of-states similarity search', 'description': 'This notebook shows how to compute the similarity of materials in terms of their electronic density-of-states (DOS), from data retrieved from the NOMAD Archive.', 'notebook_name': 'dos_similarity_search.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-dos-similarity-search', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/dos_similarity_search.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/dos_similarity_search.ipynb', 'updated': '2022-3-30', 'flags': {'featured': True, 'top_of_list': False, 'paper': False}, 'labels': {'application_section': ['Tutorials for artificial-intelligence methods'], 'application_system': ['Binaries', 'Ternaries'], 'category': ['intermediate tutorial'], 'ai_methods': ['Similarity search', 'Fingerprint'], 'platform': ['jupyter']}}, {'authors': ['Arif, Mohammad-Yasin', 'Sbailò, Luigi', 'Purcell, Thomas A. R.', 'Ghiringhelli, Luca M.', 'Scheffler, Matthias'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Predicting energy differences between crystal structures: (Meta-)stability of octet-binary compounds', 'description': 'A tool for predicting the difference in the total energy between different polymorphs for 82 octet binary compounds, which gives an indication of the stability of the material. This is accomplished by identifying a set of descriptive parameters (a descriptor) from the free-atom data for the binary atomic species comprising the material using the Sure Independent Screening (SIS) + l0-norm minimization approach.', 'notebook_name': 'descriptor_role.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-descriptor-role', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/descriptor_role.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/descriptor_role.ipynb', 'link_paper': 'https://th.fhi.mpg.de/site/uploads/Publications/PRL-114-105503-2015.pdf', 'link_doi_paper': '10.1103/PhysRevLett.114.105503', 'updated': '2021-10-18', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Octet binaries', 'Rock salt', 'Zinc blende'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Regression', 'Features selection', 'SISSO', 'Atomic features'], 'platform': ['jupyter']}}, {'authors': ['Bieniek, Björn', 'Strange, Mikkel', 'Carbogno, Christian', 'Arif, Mohammad-Yasin', 'Sbailò, Luigi', 'Scheffler, Matthias'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Error estimates from high-accuracy electronic-structure reference calculations', 'description': 'A set of tools to analyze the error in electronic structure calculations due to the choice of numerical settings. We use the NOMAD infrastructure to systematically investigate the deviances in total and relative energies as function of typical settings for basis sets, k-grids, etc. for 71 elemental and 81 binary solids in three different electronic-structure codes.', 'notebook_name': 'error_estimates.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-error-estimates', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/error_estimates.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/error_estimates.ipynb', 'link_paper': 'https://th.fhi-berlin.mpg.de/site/uploads/Publications/2008.10402.pdf', 'link_doi_paper': '10.48550/arXiv.2008.10402', 'updated': '2021-01-21', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'category': ['advanced tutorial'], 'application_system': ['Binaries', 'Elemental solids'], 'ai_methods': ['Supervised learning', 'Regression', 'Linear least-squares regression'], 'platform': ['jupyter']}}, {'authors': ['Sbailò, Luigi', 'Purcell, Thomas A. R.', 'Ghiringhelli, Luca M.', 'Scheffler, Matthias'], 'email': 'ghiringhelli@fhi-berlin.mpg.de', 'title': 'Discovery of new topological insulators in alloyed tetradymites', 'description': \"Learn how to find descriptive parameters (short formulas) that predict whether alloyed materials are topological or trivial insulators, using the example of tetradymites. This notebook is based on the algorithm 'sure independence screening and sparsifying operator' (SISSO) that enables to search for optimal descriptor by scanning huge feature spaces.\", 'notebook_name': 'tetradymite_PRM2020.ipynb', 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tetradymite-PRM2020', 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tetradymite_PRM2020.ipynb', 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/tetradymite_PRM2020.ipynb', 'link_paper': 'https://th.fhi.mpg.de/site/uploads/Publications/PhysRevMaterials.4.034204.pdf', 'link_doi_paper': '10.1103/PhysRevMaterials.4.034204', 'updated': '2020-09-15', 'flags': {'featured': True, 'top_of_list': False}, 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'], 'application_system': ['Tetradymites', 'Topological insulators'], 'category': ['advanced tutorial'], 'ai_methods': ['Supervised learning', 'Classification', 'Symbolic regression', 'Features selection', 'Atomic features', 'SISSO'], 'platform': ['jupyter']}}]\n" + ] + } + ], + "source": [ + "import json\n", + "\n", + "with open('tutorials.json', 'r') as f:\n", + " tutorials = json.load(f)['tutorials']\n", + "\n", + "print(tutorials)" + ] + }, + { + "cell_type": "code", + "execution_count": 144, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'authors',\n", + " 'description',\n", + " 'email',\n", + " 'flags',\n", + " 'labels',\n", + " 'link',\n", + " 'link_doi_paper',\n", + " 'link_paper',\n", + " 'link_public',\n", + " 'link_video',\n", + " 'notebook_name',\n", + " 'title',\n", + " 'updated',\n", + " 'url'}" + ] + }, + "execution_count": 144, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.keys()))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 145, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('flags', {'featured', 'paper', 'top_of_list'})" + ] + }, + "execution_count": 145, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('flags',{}).keys()))\n", + "'flags', keys" + ] + }, + { + "cell_type": "code", + "execution_count": 146, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'ai_methods',\n", + " 'application_keyword',\n", + " 'application_section',\n", + " 'application_system',\n", + " 'category',\n", + " 'language',\n", + " 'platform'}" + ] + }, + "execution_count": 146, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial['labels'].keys()))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 147, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'SISSO',\n", + " 'SVM',\n", + " 'archetypes',\n", + " 'clustering',\n", + " 'deep-aa',\n", + " 'k-means',\n", + " 'multi-task',\n", + " 'prototypes',\n", + " 'single-task',\n", + " 'sisso',\n", + " 'supervised',\n", + " 'training set reduction',\n", + " 'unsupervised'}" + ] + }, + "execution_count": 147, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('application_keyword',[])))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 148, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'Analysing the content of the Archive',\n", + " 'Materials property prediction',\n", + " 'Thermal Conductivity',\n", + " 'Timely artificial-intelligence applications to materials science',\n", + " 'Tutorials for artificial-intelligence methods'}" + ] + }, + "execution_count": 148, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('application_section',[])))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 149, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'Atoms',\n", + " 'Binaries',\n", + " 'Bulk properties',\n", + " 'CO2 activation',\n", + " 'Elemental solids',\n", + " 'Elements',\n", + " 'GDB molecular database',\n", + " 'GDB7',\n", + " 'Grain boundaries',\n", + " 'Heterogeneous catalysis',\n", + " 'Images',\n", + " 'Inorganic compounds',\n", + " 'Insulators',\n", + " 'Iron',\n", + " 'Low-dimensional materials',\n", + " 'Metals',\n", + " 'OQMD database',\n", + " 'Octet binaries',\n", + " 'Oxygen evolution reaction',\n", + " 'Oxygen reduction reaction',\n", + " 'Perovskite',\n", + " 'Rock salt',\n", + " 'Scaling relations',\n", + " 'Semicondictor oxides',\n", + " 'Silicon',\n", + " 'Solid State Crystals',\n", + " 'Surface',\n", + " 'Synthetic data',\n", + " 'System',\n", + " 'Ternaries',\n", + " 'Tetradymites',\n", + " 'Topological insulators',\n", + " 'Transparent conducting oxides',\n", + " 'UCI regression dataset',\n", + " 'Zinc blende',\n", + " 'matbench_expt_is_metal'}" + ] + }, + "execution_count": 149, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('application_system',[])))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 150, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'advanced tutorial',\n", + " 'beginner tutorial',\n", + " 'intermediate tutorial',\n", + " 'query tutorial',\n", + " 'thermal transport'}" + ] + }, + "execution_count": 150, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('category')))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 151, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'Atomic features',\n", + " 'Attentive response map',\n", + " 'Bagging classifier',\n", + " 'Bayesian deep learning',\n", + " 'Classification',\n", + " 'Clustering',\n", + " 'Compressed sensing',\n", + " 'Convolutional neural networks',\n", + " 'Cumulative entropy',\n", + " 'DBSCAN',\n", + " 'Decision tree',\n", + " 'Deep neural networks',\n", + " 'DenPeak',\n", + " 'Dimensionality reduction',\n", + " 'Features selection',\n", + " 'Fingerprint',\n", + " 'Gaussian approximation potentials (GAP)',\n", + " 'Gaussian mixture',\n", + " 'Gaussian process regression',\n", + " 'HDBSCAN',\n", + " 'Hierarchical clustering',\n", + " 'Information theory',\n", + " 'Kernel ridge regression',\n", + " 'LASSO',\n", + " 'Linear least-squares regression',\n", + " 'MBTR',\n", + " 'MDS',\n", + " 'Mutual information',\n", + " 'Neural networks',\n", + " 'PCA',\n", + " 'Random forest',\n", + " 'Regression',\n", + " 'SISSO',\n", + " 'SOAP',\n", + " 'SVM',\n", + " 'Sensitivy Analysis',\n", + " 'Similarity search',\n", + " 'Subgroup discovery',\n", + " 'Supervised learning',\n", + " 'Symbolic regression',\n", + " 'Symmetry functions',\n", + " 'TCMI',\n", + " 'UMAP',\n", + " 'Unsupervised learning',\n", + " 'k-means',\n", + " 'n-gram',\n", + " 't-SNE'}" + ] + }, + "execution_count": 151, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('ai_methods',[])))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 152, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'python'}" + ] + }, + "execution_count": 152, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('language',[])))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 153, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'jupyter'}" + ] + }, + "execution_count": 153, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "keys=set()\n", + "for tutorial in tutorials:\n", + " keys.update(list(tutorial.get('labels').get('platform')))\n", + "keys" + ] + }, + { + "cell_type": "code", + "execution_count": 154, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'authors': ['Arif, Mohammad-Yasin', 'Sbailò, Luigi', 'Ghiringhelli, Luca M.'],\n", + " 'email': 'ghiringhelli@fhi-berlin.mpg.de',\n", + " 'title': 'Identifying domains of applicability of machine-Learning models for materials science',\n", + " 'description': 'In this tutorial, we present a method, based on subgroup discovery, for detecting domains of applicability (DA) of ML models within a materials class. The domain of applicability of an ML model is the region of input space where the model predicts the target property with the smallest uncertainty. The utility of this approach is demonstrated by analyzing three state-of-the-art ML models for predicting the formation energy of transparent conducting oxides.',\n", + " 'notebook_name': 'domain_of_applicability.ipynb',\n", + " 'url': 'https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-domain-of-applicability',\n", + " 'link': 'https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb',\n", + " 'link_public': 'https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb',\n", + " 'link_paper': ' https://th.fhi-berlin.mpg.de/site/uploads/Publications/s41467-020-17112-9.pdf',\n", + " 'link_doi_paper': '10.1038/s41467-020-17112-9',\n", + " 'updated': '2021-01-27',\n", + " 'flags': {'featured': True, 'top_of_list': False, 'paper': True},\n", + " 'labels': {'application_section': ['Timely artificial-intelligence applications to materials science'],\n", + " 'application_system': ['Transparent conducting oxides'],\n", + " 'category': ['advanced tutorial'],\n", + " 'ai_methods': ['Supervised learning',\n", + " 'Regression',\n", + " 'Subgroup discovery',\n", + " 'Kernel ridge regression',\n", + " 'SOAP',\n", + " 'MBTR',\n", + " 'n-gram'],\n", + " 'platform': ['jupyter']}}" + ] + }, + "execution_count": 154, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tutorial = tutorials[0]\n", + "tutorial\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 155, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'last_name': 'Arif', 'first_name': 'Mohammad-Yasin'},\n", + " {'last_name': 'Sbailò', 'first_name': 'Luigi'},\n", + " {'last_name': 'Ghiringhelli',\n", + " 'first_name': 'Luca M.',\n", + " 'email': 'ghiringhelli@fhi-berlin.mpg.de'}]" + ] + }, + "execution_count": 155, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "authors=[]\n", + "for author in tutorial.get('authors'):\n", + " last_name, first_name = author.split(',', 1)\n", + " authors.append({\n", + " 'last_name':last_name.strip(),\n", + " 'first_name': first_name.strip()\n", + " })\n", + "\n", + "authors[-1]['email'] = tutorial.get('email')\n", + "authors" + ] + }, + { + "cell_type": "code", + "execution_count": 156, + "metadata": {}, + "outputs": [], + "source": [ + "def build_new_tutorial(tutorial):\n", + " new = {\n", + " \"m_def\": \"notebook_schema.schema.AIToolkitNotebook\",\n", + " 'name': tutorial['title'],\n", + " 'description': tutorial['description'],\n", + " 'date': tutorial['updated'],\n", + "\n", + "\n", + " 'notebook_path': tutorial.get('notebook_name', ''),\n", + "\n", + " 'category': tutorial['labels']['category'][0],\n", + " 'systems': tutorial['labels']['application_system'],\n", + " 'methods': tutorial['labels']['ai_methods'],\n", + " 'platform': 'Python'\n", + " }\n", + "\n", + " new['authors'] = []\n", + " for author in tutorial['authors']:\n", + " last_name, first_name = author.split(',', 1)\n", + "\n", + " new['authors'].append({\n", + " 'last_name': last_name.strip(),\n", + " 'first_name': first_name.strip()\n", + " })\n", + "\n", + " # print(tutorial.get('email'))\n", + " # new['authors'][-1]['email'] = tutorial.get('email')\n", + "\n", + " new['references'] = []\n", + "\n", + " if tutorial.get('link_doi_paper'):\n", + " new['related_publications'] = [\n", + " {\n", + " 'DOI_number': tutorial.get('link_doi_paper')\n", + " }\n", + " ]\n", + "\n", + " new['references'].append(\n", + " {\n", + " 'kind': 'article_doi',\n", + " 'url': 'https://doi.org/' + tutorial.get('link_doi_paper')\n", + " }\n", + " )\n", + "\n", + "\n", + " if tutorial.get('link'):\n", + " new['references'].append(\n", + " {\n", + " 'kind': 'hub',\n", + " 'url': tutorial['link']\n", + " }\n", + " )\n", + "\n", + "\n", + " if tutorial.get('link_paper'):\n", + " new['references'].append(\n", + " {\n", + " 'kind': 'article_url',\n", + " 'url': tutorial['link_paper']\n", + " }\n", + " )\n", + "\n", + "\n", + " if tutorial.get('url'):\n", + " new['references'].append(\n", + " {\n", + " 'kind': 'repository',\n", + " 'url': tutorial['url']\n", + " }\n", + " )\n", + "\n", + " if tutorial.get('link_video'):\n", + " new['references'].append(\n", + " {\n", + " 'kind': 'video',\n", + " 'url': tutorial['link_video']\n", + " }\n", + " )\n", + "\n", + " slug = tutorial['url'].rsplit('/', 1)[1]\n", + " return slug, {'data': new}\n", + "\n", + "\n", + "for tutorial in tutorials:\n", + " slug, new_tutorial = build_new_tutorial(tutorial)\n", + "\n", + " with open(slug+\".archive.json\", \"w\") as outfile:\n", + " json.dump(new_tutorial, outfile, indent=4)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": ".venv", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.16" + }, + "orig_nbformat": 4 + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/ai_tootlkit_notebooks/tutorials.json b/ai_tootlkit_notebooks/tutorials.json new file mode 100644 index 0000000000000000000000000000000000000000..41142240bba7c21a1d16bccc3fa0ff6745d1fd60 --- /dev/null +++ b/ai_tootlkit_notebooks/tutorials.json @@ -0,0 +1,1331 @@ +{ + "tutorials": [ + { + "authors": [ + "Arif, Mohammad-Yasin", + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Identifying domains of applicability of machine-Learning models for materials science", + "description": "In this tutorial, we present a method, based on subgroup discovery, for detecting domains of applicability (DA) of ML models within a materials class. The domain of applicability of an ML model is the region of input space where the model predicts the target property with the smallest uncertainty. The utility of this approach is demonstrated by analyzing three state-of-the-art ML models for predicting the formation energy of transparent conducting oxides.", + "notebook_name": "domain_of_applicability.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-domain-of-applicability", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/domain_of_applicability.ipynb", + "link_paper": " https://th.fhi-berlin.mpg.de/site/uploads/Publications/s41467-020-17112-9.pdf", + "link_doi_paper": "10.1038/s41467-020-17112-9", + "updated": "2021-01-27", + "flags": { + "featured": true, + "top_of_list": false, + "paper": true + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Transparent conducting oxides" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Subgroup discovery", + "Kernel ridge regression", + "SOAP", + "MBTR", + "n-gram" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Langer, Marcel F." + ], + "email": "langer@fhi-berlin.mpg.de", + "title": "cmlkit: Toolkit for Machine Learning in Materials Science and Quantum Chemistry", + "description": "In this tutorial, we will get to know cmlkit, a python package for specifying, evaluating, and optimising machine learning models, and use it to compete in the Nomad 2018 Kaggle challenge.", + "notebook_name": "cmlkit.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-cmlkit", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/cmlkit.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/cmlkit.ipynb", + "link_paper": "https://arxiv.org/pdf/2003.12081.pdf", + "link_doi_paper": "10.48550/arXiv.2003.12081", + "updated": "2021-01-14", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Transparent conducting oxides" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "SOAP", + "MBTR", + "Symmetry functions" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Foppa, Lucas", + "Hassanzada, Qaem", + "Bartel, Christopher", + "Purcell, Thomas A. R.", + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Finding a tolerance factor to predict perovskite stability with SISSO", + "description": "This tutorial shows how a tolerance factor for predicting perovskite stability can be learned from data with the sure-independece-screening-and-sparsifying-operator (SISSO) descriptor-identification approach.", + "notebook_name": "perovskites_tolerance_factor.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-perovskite-tolerance-factor", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/perovskites_tolerance_factor.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/perovskites_tolerance_factor.ipynb", + "link_paper": "https://advances.sciencemag.org/content/advances/5/2/eaav0693.full.pdf", + "link_doi_paper": "10.1126/sciadv.aav0693", + "updated": "2022-05-18", + "flags": { + "featured": true, + "top_of_list": false, + "paper": true + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "category": [ + "advanced tutorial" + ], + "application_system": [ + "Perovskite" + ], + "ai_methods": [ + "Supervised learning", + "Classification", + "Symbolic regression", + "Compressed sensing", + "SISSO", + "Decision tree", + "Features selection", + "Atomic features" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Ahmetcik, Emre", + "Ziletti, Angelo", + "Ouyang, Runhai", + "Sbail\u00f2, Luigi", + "Scheffler, Matthias", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Symbolic regression via compressed sensing: a tutorial", + "description": "In this tutorial we will show how to find descriptive parameters to predict materials properties using symbolic regrression combined with compressed sensing tools. The relative stability of the zincblende (ZB) versus rocksalt (RS) structure of binary materials is predicted and compared against a model trained with kernel ridge regression.", + "notebook_name": "compressed_sensing.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-compressed-sensing", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/compressed_sensing.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/compressed_sensing.ipynb", + "link_video": "https://www.youtube.com/watch?v=73mLp6C2opY", + "link_paper": "https://th.fhi-berlin.mpg.de/site/uploads/Publications/NJP-19-023017-2017.pdf", + "link_doi_paper": "10.1088/1367-2630/aa57bf", + "updated": "2020-09-20", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_keyword": [], + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Octet binaries" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Compressed sensing", + "Symbolic regression", + "LASSO", + "SISSO", + "Kernel ridge regression", + "Features selection", + "Atomic features" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Sbail\u00f2, Luigi", + "Scheffler, Matthias", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Querying the NOMAD Archive and performing artificial-intelligence modeling", + "description": "In this tutorial, we demonstrate how to query the NOMAD Archive from the NOMAD Analytics toolkit. We then show examples of machine learning analysis performed on the retrieved data set.", + "notebook_name": "query_nomad_archive.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-query-nomad-archive", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/query_nomad_archive.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/query_nomad_archive.ipynb", + "updated": "2021-04-14", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Analysing the content of the Archive" + ], + "application_system": [ + "Ternaries" + ], + "category": [ + "query tutorial" + ], + "ai_methods": [ + "Unsupervised learning", + "Supervised learning", + "Regression", + "Clustering", + "Dimensionality reduction", + "Random forest" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Speckhard, Daniel", + "Leitherer, Andreas", + "Ghiringhelli, Luca M." + ], + "email": "speckhard@fhi-berlin.mpg.de", + "title": "Introduction to decision-trees methods", + "description": "In this tutorial we will introduce decision trees. We go through a toy model introducing the SKLearn API. We then discuss step by step the different theoretical aspects of trees. We then move to training a regression tree and classification tree on different datasets related to materials science. We end the tutorial by covering random forests and bagging classfiers.", + "notebook_name": "decision_tree.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-decision-tree", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/decision_tree.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/decision_tree.ipynb", + "link_video": "https://www.youtube.com/watch?v=YBy9STVaqvU", + "updated": "2020-12-08", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Images", + "Metals", + "Insulators", + "matbench_expt_is_metal" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Classification", + "Decision tree", + "Random forest", + "Bagging classifier", + "Atomic features" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "sbailo@fhi-berlin.mpg.de", + "title": "Introduction to exploratory analysis (unsupervised learning) of materials spaces", + "description": "Exploratory analyses make use of unsupervised learning techniques to extract information from unknown datasets. In this tutorial, we make use of some of the most popular clustering and dimension reduction algorithms to analyze a dataset composed of 82 octet-binary compounds.", + "notebook_name": "exploratory_analysis.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-exploratory-analysis", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/exploratory_analysis.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/exploratory_analysis.ipynb", + "link_video": "https://www.youtube.com/watch?v=EJTjF9ehp7k", + "updated": "2021-02-04", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Octet binaries" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Clustering", + "Dimensionality reduction", + "k-means", + "Hierarchical clustering", + "DBSCAN", + "HDBSCAN", + "DenPeak", + "PCA", + "t-SNE", + "MDS" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Leitherer, Andreas", + "Ziletti, Angelo", + "Ghiringhelli, Luca M." + ], + "email": "leitherer@fhi-berlin.mpg.de", + "title": "ARISE - Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning", + "description": "In this tutorial, we give an introduction to ARISE (ARtificial-Intelligence-based Structure Evaluation), a powerful Bayesian-deep-neural-network tool for the recognition of atomistic structures (A. Leitherer, A. Ziletti, and L.M. Ghiringhelli, Nat. Commun. 12, 6234, 2021). ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates. By applying unsupervised learning to the internal neural-network representations, one can reveal grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties.", + "notebook_name": "ARISE.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/ARISE.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/ARISE.ipynb", + "link_paper": "https://www.nature.com/articles/s41467-021-26511-5.pdf", + "link_doi_paper": "10.1038/s41467-021-26511-5", + "updated": "2021-03-22", + "flags": { + "featured": true, + "top_of_list": false, + "paper": true + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Grain boundaries", + "Binaries", + "Ternaries", + "Low-dimensional materials" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Neural networks", + "Bayesian deep learning", + "Unsupervised learning", + "Clustering", + "Dimensionality reduction", + "HDBSCAN", + "UMAP", + "SOAP" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Fekete, \u00c1d\u00e1m", + "Stella, Martina", + "Lambert, Henry", + "De Vita, Alessandro", + "Cs\u00e1nyi, G\u00e1bor" + ], + "email": "adam.fekete@kcl.ac.uk", + "title": "The SOAP descriptor, Gaussian Approximation Potentials (GAP) and machine learning of force fields", + "description": "In this tutorial, we will be using a Gaussian Approximation Potentials to analyse results of TB DFT calculations on the Si surface. Along the way we will learn about different descriptors (2b, 3b, SOAP) to describe local atomic environment in order to predict energies and forces of the Si surface.", + "notebook_name": "gap_si_surface.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-gap-si-surface", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/gap_si_surface.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/gap_si_surface.ipynb", + "updated": "2020-06-18", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Silicon", + "Surface" + ], + "category": [ + "intermediate tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Gaussian process regression", + "Kernel ridge regression", + "SOAP", + "Gaussian approximation potentials (GAP)" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Hassanzada, Qaem", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "An introduction to support-vector machine for classification", + "description": "In this tutorial...", + "notebook_name": "svm_classification.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-svm_classification", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/svm_classification.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/svm_classification.ipynb", + "updated": "2022-03-31", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_keyword": [ + "SVM" + ], + "application_section": [ + "Materials property prediction" + ], + "application_system": [ + "Perovskite" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "SVM" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Mazheika, Aliaksei", + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M.", + "Levchenko, Sergey V.", + "Scheffler, Matthias" + ], + "email": "mazheika@fhi-berlin.mpg.de", + "title": "Subgroup discovery of catalysts\u2019 genes for carbon-dioxide activation on semiconductor oxides", + "description": "In this interactive tutorial we show the application of subgroup discovery for the search for indicators of carbond-dioxide activation with the aim of its further conversion.", + "notebook_name": "CO2_SGD.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-co2-sgd-tutorial", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/CO2_SGD.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/CO2_SGD.ipynb", + "link_paper": "https://arxiv.org/pdf/1912.06515", + "link_doi_paper": "10.48550/arXiv.1912.06515", + "updated": "2021-08-26", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "CO2 activation", + "Heterogeneous catalysis", + "Semicondictor oxides" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Subgroup discovery", + "Decision tree" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Foppa, Lucas", + "Ghiringhelli, Luca M.", + "Scheffler, Matthias" + ], + "email": "foppa@fhi-berlin.mpg.de", + "title": "Learning Design Rules for Catalysts from High-Throughput Experimentation and Theory via Subgroup Discovery", + "description": "This tutorial explores the application of subgroup discovery (SGD) to an experimental-theoretical data set in order to identify rules on key physicochemical parameters that describe the materials and environmental conditions associated with outstanding performance in heterogeneous catalysis.", + "notebook_name": "sgd_propylene_oxidation_hte.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-propylene-oxidation-hte", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_propylene_oxidation_hte.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/sgd_propylene_oxidation_hte.ipynb", + "link_paper": "https://pubs.acs.org/doi/10.1021/acscatal.1c04793", + "link_doi_paper": "10.1021/acscatal.1c04793", + "updated": "2022-2-09", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Heterogeneous catalysis" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Subgroup discovery" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Liu, Xiangyue", + "Sutton, Christopher", + "Yamamoto, Takenori", + "Blumenthal, Lars", + "Golebiowski, Jacek", + "Ziletti, Angelo", + "Scheffler, Matthias", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "2018 NOMAD-Kaggle research competition", + "description": "In this tutorial, we will explore the best results of the NOMAD 2018 Kaggle research competition. The goal of this competition was to develop machine-learning models for the prediction of two target properties: the formation energy and the bandgap energy of transparent semiconducting oxides. The purpose of the modelling is to facilitate the discovery of new such materials and allow for advancements in (opto)electronic technologies", + "notebook_name": "kaggle_competition.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kaggle-competition", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kaggle_competition.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/kaggle_competition.ipynb", + "link_paper": "https://th.fhi.mpg.de/site/uploads/Publications/s41524-019-0239-3.pdf", + "link_doi_paper": "10.1038/s41524-019-0239-3", + "updated": "2021-01-19", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Transparent conducting oxides" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "Neural networks", + "SOAP", + "n-gram" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Naik ,Aakash A.", + "Sbail\u00f2, Luigi", + "Ahmetcik, Emre", + "Ziletti, Angelo", + "Ouyang, Runhai", + "Ghiringhelli, Luca M.", + "Scheffler, Matthias" + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Predicting the metal-insulator classification of elements and binary systems", + "description": "This tutorial shows how to find descriptive parameters (short formulas) for the classification of materials properties. As an example, we address the classification of elemental and binary systems Ax\u200b\u200bBy\u200b\u200b into metals and non metals using experimental data extracted from the SpringerMaterials data base. The method is based on the algorithm sure independence screening and sparsifying operator (SISSO), which enables to search for optimal descriptors by scanning huge feature spaces. ", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-metalinsulator-prm2018", + "link": "", + "link_public": "", + "updated": "2021-12-1", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Binaries", + "Elements" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "SISSO", + "Classification" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Ziletti, Angelo", + "Leitherer, Andreas", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Introduction to convolutional neural networks", + "description": "In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model with Keras, and explain the classification decision process using attentive response maps.", + "notebook_name": "convolutional_nn.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-convolutional-nn", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/convolutional_nn.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/convolutional_nn.ipynb", + "link_video": "https://youtu.be/MST8X1yCWK8", + "updated": "2021-01-29", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Images" + ], + "category": [ + "intermediate tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Classification", + "Neural networks", + "Convolutional neural networks", + "Attentive response map" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Foppa, Lucas", + "Purcell, Thomas A. R.", + "Levchenko, Sergey V.", + "Scheffler, Matthias", + "Ghiringhelli, Luca M." + ], + "email": "foppa@fhi-berlin.mpg.de", + "title": "Hierarchical symbolic regression for identifying key physical parameters correlated with materials properties", + "description": "In this notebook, we describe a hierarchical symbolic-regression approach for finding, based on data, analytical expressions relating materials properties to simpler physicochemical parameters associated with the underlying processes governing the properties.", + "notebook_name": "hierarchical_sisso.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-hierarchical-sisso", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/hierarchical_sisso.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/hierarchical_sisso.ipynb", + "link_paper": "https://journals.aps.org/prl/pdf/10.1103/PhysRevLett.129.055301", + "link_doi_paper": "10.1103/PhysRevLett.129.055301", + "updated": "2022-8-3", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Bulk properties" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "SISSO" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Fekete, \u00c1d\u00e1m", + "Stella, Martina", + "Lambert, Henry", + "De Vita, Alessandro", + "Cs\u00e1nyi, G\u00e1bor" + ], + "email": "adam.fekete@kcl.ac.uk", + "title": "Structure similarity and structure-property relationship: grain boundaries of alpha-Fe", + "description": "In this tutorial, we will be using a machine-learning method (clustering) to analyse results of grain-boundary (GB) calculations of alpha-iron. Along the way, we will learn about different methods to describe local atomic environment in order to calculate properties of GBs. We will use these properties to separate the different regions of the GB using clustering methods. Finally we will determine how the energy of the GB is changing according to the angle difference of the regions.", + "notebook_name": "grain_boundaries.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-grain-boundaries", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/grain_boundaries.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/grain_boundaries.ipynb", + "link_paper": "https://www.sciencedirect.com/science/article/pii/S0010465518301450?via%3Dihub", + "link_doi_paper": "10.1016/j.cpc.2018.04.029", + "updated": "2020-01-18", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Iron", + "Grain boundaries" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Unsupervised learning", + "Supervised learning", + "Clustering", + "Regression", + "k-means", + "Gaussian mixture" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Foppa, Lucas", + "Ghiringhelli, Luca M.", + "Scheffler, Matthias" + ], + "email": "foppa@fhi-berlin.mpg.de", + "title": "Materials genes of heterogeneous catalysis from clean experiments and artificial intelligence", + "description": "This tutorial explores the application of SISSO to a consistent experimental data set in order to identify the key parameters correlated with the catalyst selectivity in propane oxidation.", + "notebook_name": "catalysis_MRS2021.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/PropaneOxidation", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/catalysis_MRS2021.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/catalysis_MRS2021.ipynb", + "link_paper": "https://link.springer.com/article/10.1557/s43577-021-00165-6", + "link_doi_paper": "10.1557/s43577-021-00165-6", + "updated": "2022-6-23", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Heterogeneous catalysis" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "SISSO" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Naik ,Aakash A.", + "Ghiringhelli, Luca M." + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Atomic-features-package usage demonstration", + "description": "In this tutorial, we show how the atomic-features-package can be accessed and used to explore the atomic features form various sources and to prepare the input features for machine-learning studies.", + "notebook_name": "atomic_features.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-atomic-features", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/atomic_features.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/atomic_features.ipynb", + "updated": "2021-12-07", + "labels": { + "application_system": [ + "Atoms" + ], + "category": [ + "query tutorial" + ], + "platform": [ + "jupyter" + ], + "ai_methods": [ + ] + } + }, + { + "authors": [ + "Regler, Benjamin", + "Scheffler, Matthias", + "Ghiringhelli, Luca M." + ], + "email": "regler@fhi-berlin.mpg.de", + "title": "Introduction to total cumulative mutual information", + "description": "This interactive notebook introduces the concepts and original implementation of total cumulative mutual information (TCMI), as presented in the related publication. The main results of the publication are also reproduced in a hands-on style", + "notebook_name": "tcmi.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tcmi", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tcmi.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/tcmi.ipynb", + "link_paper": "https://arxiv.org/pdf/2001.11212", + "link_doi_paper": "10.48550/arXiv.2001.11212", + "updated": "2020-02-06", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Synthetic data", + "UCI regression dataset", + "Octet binaries" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Unsupervised learning", + "Features selection", + "Information theory", + "Mutual information", + "Cumulative entropy", + "Clustering", + "TCMI" + ], + "language": [ + "python" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Cs\u00e1nyi, G\u00e1bor", + "Kermode, James R." + ], + "email": "gc121@cam.ac.uk", + "title": "Machine learning atomic charges", + "description": "In this tutorial, we will use Gaussian process regression, GPR (or equivalently, Kernel Ridge Regression, KRR) to train and predict charges on atoms in small organic molecules.", + "notebook_name": "soap_atomic_charges.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-soap-atomic-charges", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/soap_atomic_charges.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/soap_atomic_charges.ipynb", + "updated": "2019-09-26", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "GDB molecular database", + "GDB7" + ], + "category": [ + "intermediate tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Gaussian process regression", + "Kernel ridge regression", + "SOAP" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Oehlers, Milena", + "Sbail\u00f2, Luigi" + ], + "email": "milenaoehlers@gmail.com", + "title": "Proto- and Archetype Clustering-based SISSO", + "description": "In this tutorial two clustering methods, namely unsupervised k-means and supervised deep-aa, will be used to extract proto- and archetypes, respectively, along with corresponding clusters. The set of proto- or archetypes can be used as a substantially reduced training set for Single-Task SISSO, which outperforms random selection, while the corresponding clusters allow for an educated material2task-assignment of all training and test materials for Multi-Task SISSO, whose training on the whole training set outperforms corresponding training of Single-Task SISSO.", + "notebook_name": "proto_archetype_clustering_sisso.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/proto_archetype_clustering_sisso", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/proto_archetype_clustering_sisso.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/proto_archetype_clustering_sisso.ipynb", + "updated": "2021-12-20", + "flags": { + "featured": false, + "top_of_list": false + }, + "labels": { + "application_keyword": [ + "k-means", + "deep-aa", + "SISSO", + "sisso", + "archetypes", + "prototypes", + "clustering", + "training set reduction", + "multi-task", + "single-task", + "unsupervised", + "supervised" + ], + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "System" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Clustering", + "SISSO" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Leitherer, Andreas", + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "leitherer@fhi-berlin.mpg.de", + "title": "Introduction to multilayer perceptrons (deep neural networks)", + "description": "In this tutorial, we discuss how multilayer perceptrons, a standard neural-network architecture, can be employed for regression tasks. Specifically, we will use the ElemNet neural-network architecture to predict the volume per atom of inorganic compounds, where the Open Quantum Materials Database (OQMD) is used as a resource.", + "notebook_name": "nn_regression.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/nn_regression.ipynb", + "link_public": "https://nomad-lab.eu/prod/analytics/public/user-redirect/notebooks/tutorials/nn_regression.ipynb", + "link_video": "https://www.youtube.com/watch?v=U0lI5n8Hleo", + "updated": "2021-01-29", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Materials property prediction" + ], + "application_system": [ + "Inorganic compounds", + "OQMD database" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Neural networks", + "Deep neural networks", + "Atomic features" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Langer, Marcel F." + ], + "email": "langer@fhi-berlin.mpg.de", + "title": "Introduction to kernel ridge regression for materials-property prediction", + "description": "In this tutorial, we will explore the application of kernel ridge regression to the prediction of materials properties. We will begin with a largely informal, pragmatic introduction to kernel ridge regression, including a rudimentary implementation, in order to become familiar with the basic terminology and considerations. We will then discuss representations, and re-trace the NOMAD 2018 Kaggle challenge.", + "notebook_name": "krr4mat.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-krr4mat", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/krr4mat.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/krr4mat.ipynb", + "link_video": "https://www.youtube.com/watch?v=H_MVlljpYHw", + "updated": "2020-12-15", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Transparent conducting oxides" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Kernel ridge regression", + "SOAP" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Purcell, Thomas A. R.", + "Scheffler, Matthias", + "Ghiringhelli, Luca M.", + "Carbogno, Christian" + ], + "email": "purcell@fhi-berlin.mpg.de", + "title": "Accelerated Materials Exploration via AI-Generated Maps", + "description": "Notebook recreating the results of the paper by the same title and authors.", + "notebook_name": "kappa_screening_sisso.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-kappa_L_learning", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/kappa_screening_sisso.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/kappa_screening_sisso.ipynb", + "updated": "2022-06-17", + "flags": { + "featured": true, + "top_of_list": false, + "paper": true + }, + "labels": { + "application_section": [ + "Thermal Conductivity" + ], + "application_system": [ + "Solid State Crystals" + ], + "category": [ + "thermal transport" + ], + "ai_methods": [ + "SISSO", + "Sensitivy Analysis" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Sbail\u00f2, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "sbailo@fhi-berlin.mpg.de", + "title": "Introduction to clustering", + "description": "In this tutorial, we introduce to the most popular clustering algorithms. We focus on partitioning, hierarchical and density-based clustering algorithms. The methods are tested on synthetic datasets of increasing complexity", + "notebook_name": "clustering_tutorial.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-clustering-tutorial", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/clustering_tutorial.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/clustering_tutorial.ipynb", + "updated": "2021-01-21", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Synthetic data" + ], + "category": [ + "beginner tutorial" + ], + "ai_methods": [ + "Unsupervised learning", + "Clustering", + "k-means", + "Hierarchical clustering", + "DBSCAN", + "HDBSCAN" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Foppa, Lucas", + "Ghiringhelli, Luca M." + ], + "email": "foppa@fhi-berlin.mpg.de", + "title": "Introduction to subgroup discovery: Identifying outstanding transition-metal-alloy catalysts", + "description": "This tutorial introduces, by means of two applications in materials science, the artificial-intelligence technique subgroup discovery.", + "notebook_name": "sgd_alloys_oxygen_reduction_evolution.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-sgd-alloys-oxygen-reduction-evolution", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/sgd_alloys_oxygen_reduction_evolution.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/sgd_alloys_oxygen_reduction_evolution.ipynb", + "link_paper": "https://link.springer.com/content/pdf/10.1007/s11244-021-01502-4.pdf", + "link_doi_paper": "10.1007/s11244-021-01502-4", + "updated": "2021-10-28", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Heterogeneous catalysis", + "Oxygen evolution reaction", + "Oxygen reduction reaction", + "Scaling relations" + ], + "category": [ + "intermediate tutorial" + ], + "ai_methods": [ + "Subgroup discovery", + "Decision tree" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Gabaj, \u0160imon", + "Kuban, Martin", + "Rigamonti, Santiago", + "Draxl, Claudia" + ], + "email": "gabajsim@physik.hu-berlin.de", + "title": "Electronic density-of-states similarity search", + "description": "This notebook shows how to compute the similarity of materials in terms of their electronic density-of-states (DOS), from data retrieved from the NOMAD Archive.", + "notebook_name": "dos_similarity_search.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-dos-similarity-search", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/dos_similarity_search.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/dos_similarity_search.ipynb", + "updated": "2022-3-30", + "flags": { + "featured": true, + "top_of_list": false, + "paper": false + }, + "labels": { + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "Binaries", + "Ternaries" + ], + "category": [ + "intermediate tutorial" + ], + "ai_methods": [ + "Similarity search", + "Fingerprint" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Arif, Mohammad-Yasin", + "Sbail\u00f2, Luigi", + "Purcell, Thomas A. R.", + "Ghiringhelli, Luca M.", + "Scheffler, Matthias" + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Predicting energy differences between crystal structures: (Meta-)stability of octet-binary compounds", + "description": "A tool for predicting the difference in the total energy between different polymorphs for 82 octet binary compounds, which gives an indication of the stability of the material. This is accomplished by identifying a set of descriptive parameters (a descriptor) from the free-atom data for the binary atomic species comprising the material using the Sure Independent Screening (SIS) + l0-norm minimization approach.", + "notebook_name": "descriptor_role.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-descriptor-role", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/descriptor_role.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/descriptor_role.ipynb", + "link_paper": "https://th.fhi.mpg.de/site/uploads/Publications/PRL-114-105503-2015.pdf", + "link_doi_paper": "10.1103/PhysRevLett.114.105503", + "updated": "2021-10-18", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Octet binaries", + "Rock salt", + "Zinc blende" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Features selection", + "SISSO", + "Atomic features" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Bieniek, Bj\u00f6rn", + "Strange, Mikkel", + "Carbogno, Christian", + "Arif, Mohammad-Yasin", + "Sbail\u00f2, Luigi", + "Scheffler, Matthias" + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Error estimates from high-accuracy electronic-structure reference calculations", + "description": "A set of tools to analyze the error in electronic structure calculations due to the choice of numerical settings. We use the NOMAD infrastructure to systematically investigate the deviances in total and relative energies as function of typical settings for basis sets, k-grids, etc. for 71 elemental and 81 binary solids in three different electronic-structure codes.", + "notebook_name": "error_estimates.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-error-estimates", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/error_estimates.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/error_estimates.ipynb", + "link_paper": "https://th.fhi-berlin.mpg.de/site/uploads/Publications/2008.10402.pdf", + "link_doi_paper": "10.48550/arXiv.2008.10402", + "updated": "2021-01-21", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "category": [ + "advanced tutorial" + ], + "application_system": [ + "Binaries", + "Elemental solids" + ], + "ai_methods": [ + "Supervised learning", + "Regression", + "Linear least-squares regression" + ], + "platform": [ + "jupyter" + ] + } + }, + { + "authors": [ + "Sbail\u00f2, Luigi", + "Purcell, Thomas A. R.", + "Ghiringhelli, Luca M.", + "Scheffler, Matthias" + ], + "email": "ghiringhelli@fhi-berlin.mpg.de", + "title": "Discovery of new topological insulators in alloyed tetradymites", + "description": "Learn how to find descriptive parameters (short formulas) that predict whether alloyed materials are topological or trivial insulators, using the example of tetradymites. This notebook is based on the algorithm 'sure independence screening and sparsifying operator' (SISSO) that enables to search for optimal descriptor by scanning huge feature spaces.", + "notebook_name": "tetradymite_PRM2020.ipynb", + "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tetradymite-PRM2020", + "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/tetradymite_PRM2020.ipynb", + "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/tetradymite_PRM2020.ipynb", + "link_paper": "https://th.fhi.mpg.de/site/uploads/Publications/PhysRevMaterials.4.034204.pdf", + "link_doi_paper": "10.1103/PhysRevMaterials.4.034204", + "updated": "2020-09-15", + "flags": { + "featured": true, + "top_of_list": false + }, + "labels": { + "application_section": [ + "Timely artificial-intelligence applications to materials science" + ], + "application_system": [ + "Tetradymites", + "Topological insulators" + ], + "category": [ + "advanced tutorial" + ], + "ai_methods": [ + "Supervised learning", + "Classification", + "Symbolic regression", + "Features selection", + "Atomic features", + "SISSO" + ], + "platform": [ + "jupyter" + ] + } + } + ] +} diff --git a/nomad.yaml b/nomad.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a840ac5cf73dc79cacbe7527cb21f43b5325a3fc --- /dev/null +++ b/nomad.yaml @@ -0,0 +1,252 @@ +keycloak: + realm_name: fairdi_nomad_test + +normalize: + normalizers: + include: + - MetainfoNormalizer + +plugins: + include: + - schemas/aitoolkit + # exclude: + # - parsers/nexus + options: + schemas/aitoolkit: + python_package: nomad_aitoolkit_notebook +ui: + apps: + include: + # - 'entries' + - 'aitoolkit' + options: + aitoolkit: + label: AI Toolkit + path: aitoolkit + # resource: entries + # breadcrumb: AI Toolkit notebook + category: Notebooks + description: Search AI Toolkit notebooks + # help: + # title: AI Toolkit notebook search + # content: | + # This page allows you to specifically seach **Jupyter + # Notebook** within NOMAD. It is very similar + # to the entries search, but with a reduced filter set and + # specialized arrangement of default columns. + schemas: + include: + - 'notebook_schema.schema.AIToolkitNotebook' + columns: + selected: + - 'data.name#notebook_schema.schema.AIToolkitNotebook' + - 'authors' + - 'data.category#notebook_schema.schema.AIToolkitNotebook' + - 'data.date#notebook_schema.schema.AIToolkitNotebook' + # - 'entry_type' + # - 'upload_create_time' + - references + include: + - 'data.name#notebook_schema.schema.AIToolkitNotebook' + - 'data.category#notebook_schema.schema.AIToolkitNotebook' + - 'data.systems#notebook_schema.schema.AIToolkitNotebook' + - 'data.methods#notebook_schema.schema.AIToolkitNotebook' + - 'data.platform#notebook_schema.schema.AIToolkitNotebook' + - 'data.date#notebook_schema.schema.AIToolkitNotebook' + - 'entry_type' + - 'upload_create_time' + - 'authors' + - 'references' + options: + data.name#notebook_schema.schema.AIToolkitNotebook: + label: Name + align: left + data.category#notebook_schema.schema.AIToolkitNotebook: + label: Category + data.systems#notebook_schema.schema.AIToolkitNotebook: + label: Systems + data.methods#notebook_schema.schema.AIToolkitNotebook: + label: Methods + data.platform#notebook_schema.schema.AIToolkitNotebook: + label: Platform + data.date#notebook_schema.schema.AIToolkitNotebook: + label: Upload time + align: left + entry_type: + label: Entry type + align: left + upload_create_time: + label: Upload time + align: left + authors: + label: Authors + align: left + references: + label: References + align: left + # filter_menus: + # options: + # notebook: + # label: Notebook Quantities + # level: 0 + # custom_quantities: + # label: User Defined Quantities + # level: 0 + # size: l + # author: + # label: Author / Origin / Dataset + # level: 0 + # size: m + # metadata: + # label: Visibility / IDs / Schema + # level: 0 + # optimade: + # label: Optimade + # level: 0 + # size: m + filter_menus: + options: + material: {'label': 'Material', 'level': 0} + elements: {'label': 'Elements / Formula', 'level': 1, 'size': 'xl'} + structure: {'label': 'Structure', 'level': 1} + custom_quantities: {'label': 'User Defined Quantities', 'level': 0, 'size': 'l'} + author: {'label': 'Author / Origin / Dataset', 'level': 0, 'size': 'm'} + metadata: {'label': 'Visibility / IDs / Schema', 'level': 0} + optimade: {'label': 'Optimade', 'level': 0, 'size': 'm'} + # filters_locked: + # entry_type: AIToolkitNotebook + filters_locked: + section_defs.definition_qualified_name: 'notebook_schema.schema.AIToolkitNotebook' + dashboard: + widgets: + - type: terms + # showinput: true + scale: linear + quantity: data.category#notebook_schema.schema.AIToolkitNotebook + layout: + xxl: + minH: 3 + minW: 3 + h: 6 + w: 6 + y: 0 + x: 0 + xl: + minH: 3 + minW: 3 + h: 6 + w: 6 + y: 0 + x: 0 + lg: + minH: 3 + minW: 3 + h: 6 + w: 6 + y: 0 + x: 0 + md: + minH: 3 + minW: 3 + h: 4 + w: 6 + y: 0 + x: 0 + sm: + minH: 3 + minW: 3 + h: 3 + w: 6 + y: 0 + x: 0 + # - type: terms + # # showinput: true + # scale: linear + # quantity: data.methods#notebook_schema.schema.AIToolkitNotebook + # layout: + # xxl: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 6 + # xl: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 6 + # lg: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 6 + # md: + # minH: 3 + # minW: 3 + # h: 4 + # w: 6 + # y: 0 + # x: 6 + # sm: + # minH: 3 + # minW: 3 + # h: 3 + # w: 6 + # y: 0 + # x: 6 + # - type: terms + # # showinput: true + # scale: linear + # quantity: data.systems#notebook_schema.schema.AIToolkitNotebook + # layout: + # xxl: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 12 + # xl: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 12 + # lg: + # minH: 3 + # minW: 3 + # h: 6 + # w: 6 + # y: 0 + # x: 12 + # md: + # minH: 3 + # minW: 3 + # h: 4 + # w: 6 + # y: 0 + # x: 12 + # sm: + # minH: 3 + # minW: 3 + # h: 3 + # w: 6 + # y: 3 + # x: 0 + rows: + actions: + enabled: true + details: + enabled: true + selection: + enabled: true + # filters: + # exclude: + # - mainfile + # - combine diff --git a/nomad_aitoolkit_notebook/__init__.py b/nomad_aitoolkit_notebook/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..c0048de89e730be3657cdc8a78acb8e3eff4c3fb --- /dev/null +++ b/nomad_aitoolkit_notebook/__init__.py @@ -0,0 +1 @@ +from .schema import Notebook, AIToolkitNotebook diff --git a/nomad_aitoolkit_notebook/nomad_plugin.yaml b/nomad_aitoolkit_notebook/nomad_plugin.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a48dbc715f0e74e69b669790d0b594fcea9d0cb0 --- /dev/null +++ b/nomad_aitoolkit_notebook/nomad_plugin.yaml @@ -0,0 +1,4 @@ +plugin_type: schema +name: NOMAD's notebook schema plugin +description: | + Describes the basic schemas for user-defined and ai toolkit notebooks. \ No newline at end of file diff --git a/nomad_aitoolkit_notebook/schema.py b/nomad_aitoolkit_notebook/schema.py new file mode 100644 index 0000000000000000000000000000000000000000..f09738a72f8340785de32806f550499dabd6511a --- /dev/null +++ b/nomad_aitoolkit_notebook/schema.py @@ -0,0 +1,133 @@ +from nomad.metainfo import Quantity, Package, Section, MEnum, Datetime, MSection, SubSection +from nomad.datamodel.data import EntryData, ArchiveSection, Author, AuthorReference +from nomad.datamodel.metainfo.annotations import ELNAnnotation, ELNComponentEnum +from nomad.datamodel.metainfo.basesections import PublicationReference +import numpy as np + +from nomad_notebook.schema import BaseNotebook, Reference + +m_package = Package(name='AI Toolkit Notebook Schema') + + +class AIToolkitNotebook(BaseNotebook): + + m_def = Section( + label='AI Toolkit Notebook', + # categories=[NotebookCategory], + a_eln=ELNAnnotation( + properties=dict( + order=[ + 'name', + 'description', + 'authors', + 'date', + 'notebook_path', + 'category', + 'methods', + 'systems', + 'platform', + ] + ) + ) + ) + + authors = Quantity( + type=Author, + shape=['*'], + a_eln=ELNAnnotation(component=ELNComponentEnum.AuthorEditQuantity), + ) + + date = Quantity( + type=Datetime, + a_eln=ELNAnnotation(component=ELNComponentEnum.DateTimeEditQuantity), + description='For testing datetime field.' + ) + + notebook_path = Quantity( + type=str, + description=''' + The relative path to the .ipynb file inside docker deployment. + ''', + a_eln=ELNAnnotation(component=ELNComponentEnum.StringEditQuantity, label='Path of notebook'), + ) + + systems = Quantity( + type=str, + shape=['*'], + a_eln=ELNAnnotation( + component=ELNComponentEnum.EnumEditQuantity, + props=dict( + suggestions=[ + 'Atoms', + 'Binaries', + 'Bulk properties', + 'CO2 activation', + 'Elemental solids', + 'Elements', + 'GDB molecular database', + 'GDB7', + 'Grain boundaries', + 'Heterogeneous catalysis', + 'Images', + 'Inorganic compounds', + 'Insulators', + 'Iron', + 'Low-dimensional materials', + 'Metals', + 'OQMD database', + 'Octet binaries', + 'Oxygen evolution reaction', + 'Oxygen reduction reaction', + 'Perovskite', + 'Rock salt', + 'Scaling relations', + 'Semicondictor oxides', + 'Silicon', + 'Solid State Crystals', + 'Surface', + 'Synthetic data', + 'System', + 'Ternaries', + 'Tetradymites', + 'Topological insulators', + 'Transparent conducting oxides', + 'UCI regression dataset', + 'Zinc blende', + 'matbench_expt_is_metal' + ] + ) + ), + ) + + # repository = Quantity( + # type=str, + # a_eln=dict(component='URLEditQuantity', label='Git repository') + # ) + # + # image = Quantity( + # type=str, + # a_eln=dict(component='StringEditQuantity', label='Docker image') + # ) + # + # video_url = Quantity( + # type=str, + # a_eln=dict(component='URLEditQuantity', label='Video url') + # ) + + def normalize(self, archive, logger): + super().normalize(archive, logger) + + if self.authors: + archive.data.notebook_authors = [ + AuthorReference().resolve(author) for author in self.authors + ] + + if self.references: + for reference in self.references: + if reference.kind != 'hub': + continue + archive.metadata.default_launch_url = reference.url + break + + +m_package.__init_metainfo__()