Training sets based on uncertainty estimates in the cluster-expansion method
JSON Export
{
"metadata": {
"edited_by": 576,
"owner": 665,
"description": "Cluster expansion (CE) has gained an increasing level of popularity in recent years, and many strategies have been proposed for training and fitting the CE models to first-principles calculation results. The paper reports a new strategy for constructing a training set based on their relevance in Monte Carlo sampling for statistical analysis and reduction of the expected error. We call the new strategy a \"bootstrapping uncertainty structure selection\" (BUSS) scheme and compared its performance against a popular scheme where one uses a combination of random structure and ground-state search (referred to as RGS). The provided dataset contains the training sets generated using BUSS and RGS for constructing a CE model for disordered Cu2ZnSnS4 material. The files are in the format of the Atomic Simulation Environment (ASE) database (please refer to ASE documentation for more information https://wiki.fysik.dtu.dk/ase/index.html). Each `.db` file contains 100 DFT calculations, which were generated using iteration cycles. Each iteration cycle is referred to as a generation (marked with `gen` key in the database) and each database contains 10 generations where each generation consists of 10 training structures. See more details in the paper.",
"keywords": [
"BIG-MAP",
"cluster expansion",
"Monte Carlo",
"phase transition",
"bootstrapping",
"machine learning",
"energy materials"
],
"is_last": true,
"title": "Training sets based on uncertainty estimates in the cluster-expansion method",
"status": "published",
"license_addendum": null,
"doi": "10.24435/materialscloud:ha-ca",
"conceptrecid": "1239",
"_files": [
{
"checksum": "md5:b894ad3a6916a4f3ca6b2da0d4b5fd49",
"description": "ASE database containing the training structures generated using BUSS scheme",
"key": "buss.db",
"size": 995328
},
{
"checksum": "md5:4bbbc675bdfcb53813ca300e9a68da2a",
"description": "ASE database containing the training structures generated using RGS scheme",
"key": "rgs.db",
"size": 557056
}
],
"references": [
{
"citation": "D. Kleiven, J. Akola, A. Peterson, T. Vegge, J.H. Chang, J. Phys. Energy 3 034012 (2021)",
"comment": "Paper in which the method is described",
"url": "https://iopscience.iop.org/article/10.1088/2515-7655/abf9ef/meta",
"doi": "10.1088/2515-7655/abf9ef",
"type": "Journal reference"
}
],
"contributors": [
{
"givennames": "David",
"affiliations": [
"Department of Physics, Norwegian University of Science and Technology, NO-7491 Trondheim, Norway"
],
"familyname": "Kleiven",
"email": "david.kleiven@ntnu.no"
},
{
"givennames": "Jaakko",
"affiliations": [
"Department of Physics, Norwegian University of Science and Technology, NO-7491 Trondheim, Norway",
"Computational Physics Laboratory, Tampere University, P.O. Box 692, FI-33014 Tampere, Finland"
],
"familyname": "Akola"
},
{
"givennames": "Andrew",
"affiliations": [
"School of Engineering, Brown University, Providence, RI 02912, United States of America",
"Department of Energy Conversion and Storage, Technical University of Denmark, DK-2800 Kgs. Lyngby, Denmark"
],
"familyname": "Peterson"
},
{
"givennames": "Tejs",
"affiliations": [
"Department of Energy Conversion and Storage, Technical University of Denmark, DK-2800 Kgs. Lyngby, Denmark"
],
"familyname": "Vegge"
},
{
"givennames": "Jin Hyun",
"affiliations": [
"Department of Energy Conversion and Storage, Technical University of Denmark, DK-2800 Kgs. Lyngby, Denmark"
],
"familyname": "Chang",
"email": "jchang@dtu.dk"
}
],
"_oai": {
"id": "oai:materialscloud.org:1240"
},
"publication_date": "Feb 03, 2022, 17:42:15",
"mcid": "2022.21",
"version": 1,
"id": "1240",
"license": "Creative Commons Attribution 4.0 International"
},
"revision": 4,
"created": "2022-02-01T11:34:43.314804+00:00",
"id": "1240",
"updated": "2022-02-03T16:42:15.908447+00:00"
}