diff --git a/src/toolkitMetadata.json b/src/toolkitMetadata.json
index 1afbcfbe00ff5c925148146fe09ba94ddc7dcb06..0e3b36008156ad1f2945dc6aa24071220f74033a 100644
--- a/src/toolkitMetadata.json
+++ b/src/toolkitMetadata.json
@@ -1,55 +1,5 @@
{
"tutorials": [
- {
- "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": "https://www.nature.com/articles/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",
- "Dimension reduction",
- "HDBSCAN",
- "UMAP",
- "SOAP"
- ],
- "platform": [
- "jupyter"
- ]
- }
- },
{
"authors": [
"Naik ,Aakash A.",
@@ -520,96 +470,6 @@
]
}
},
- {
- "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": [
- "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": "https://www.sciencedirect.com/science/article/pii/S0010465518301450/pdfft?md5=f21651f69edad3505ed3dd3ba38aee18&pid=1-s2.0-S0010465518301450-main.pdf",
- "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": [
"Liu, Xiangyue",
@@ -869,46 +729,6 @@
]
}
},
- {
- "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": [
"Regler, Benjamin",