|
Persistent Identifier
|
perma:LIST.TLRRSF |
|
Publication Date
|
2026-07-06 |
|
Title
| Crash testing machine learning force fields for molecules, materials, and interfaces: model analysis in the TEA Challenge 2023 [* Cross-Reference *] |
|
Other Identifier
| https://doi.org/10.1039/d4sc06529h
SCOPUS_ID:85216839949 |
|
Author
| Poltavsky, Igor (University of Luxembourg) - ORCID: 0000-0002-3188-7017
Charkin-Gorbulin, Anton (University of Luxembourg, Université de Mons)
Puleva, Mirela (University of Luxembourg, University of Luxembourg)
Fonseca, Grégory (University of Luxembourg)
Batatia, Ilyes (Department of Engineering)
Browning, Nicholas J. (Centro Svizzero di Calcolo Scientifico)
Chmiela, Stefan (Technische Universität Berlin, BIFOLD)
Cui, Mengnan (Fritz Haber Institute of the Max Planck Society)
Frank, J. Thorben (Technische Universität Berlin, BIFOLD) - ORCID: 0000-0002-6234-4736
Heinen, Stefan (Vector Institute)
Huang, Bing (Wuhan University)
Käser, Silvan (Universität Basel) - ORCID: 0000-0002-3641-8519
Kabylda, Adil (University of Luxembourg) - ORCID: 0000-0002-8620-6135
Khan, Danish (Vector Institute, University of Toronto)
Müller, Carolin (Friedrich-Alexander-Universität Erlangen-Nürnberg) - ORCID: 0000-0002-5968-2216
Price, Alastair J.A. (University of Toronto, University of Toronto)
Riedmiller, Kai (Heidelberg Institute for Theoretical Studies (HITS GmbH)) - ORCID: 0000-0003-1738-754X
Töpfer, Kai (Universität Basel) - ORCID: 0000-0002-4650-9641
Ko, Tsz Wai (Aiiso Yufeng Li Family Department of Chemical and Nano Engineering)
Meuwly, Markus (Universität Basel) - ORCID: 0000-0001-7930-8806
Rupp, Matthias (Luxembourg Institute of Science and Technology) - ORCID: 0000-0002-2934-2958
Csányi, Gábor (Department of Engineering) - ORCID: 0000-0002-8180-2034
von Lilienfeld, O. Anatole (Technische Universität Berlin, BIFOLD, Vector Institute, University of Toronto, University of Toronto, University of Toronto, University of Toronto) - ORCID: 0000-0001-7419-0466
Margraf, Johannes T. (Universität Bayreuth)
Müller, Klaus Robert (Technische Universität Berlin, BIFOLD, Korea University, Max Planck Institute for Informatics, DeepMind Technologies Limited) - ORCID: 0000-0002-3861-7685
Tkatchenko, Alexandre (University of Luxembourg, University of Luxembourg) - ORCID: 0000-0002-1012-4854 |
|
Point of Contact
|
Use email button above to contact.
LIST RDS (LIST) |
|
Description
| Atomistic simulations are routinely employed in academia and industry to study the behavior of molecules, materials, and their interfaces. Central to these simulations are force fields (FFs), whose development is challenged by intricate interatomic interactions at different spatio-temporal scales and the vast expanse of chemical space. Machine learning (ML) FFs, trained on quantum-mechanical energies and forces, have shown the capacity to achieve sub-kcal (mol−1 Å−1) accuracy while maintaining computational efficiency. The TEA Challenge 2023 rigorously evaluated commonly used MLFFs across diverse applications, highlighting their strengths and weaknesses. Participants trained their models using provided datasets, and the results were systematically analyzed to assess the ability of MLFFs to reproduce potential energy surfaces, handle incomplete reference data, manage multi-component systems, and model complex periodic structures. This publication describes the datasets, outlines the proposed challenges, and presents a detailed analysis of the accuracy, stability, and efficiency of the MACE, SO3krates, sGDML, SOAP/GAP, and FCHL19* architectures in molecular dynamics simulations. The models represent the MLFF developers who participated in the TEA Challenge 2023. All results presented correspond to the state of the ML architectures as of October 2023. A comprehensive analysis of the molecular dynamics results obtained with different MLFFs will be presented in the second part of this manuscript. (2025-02-10)
***This entry has been automatically imported via Infodoc(ASO) CSV by LIST harvest scripts. Please refer to https://doi.org/10.1039/d4sc06529h for the original and latest version of the dataset and data downloads*** (2026-06-09) |
|
Subject
| Physics |
|
Keyword
| behavior of molecules
routinely employed
employed in academia
academia and industry
industry to study |
|
Funding Information
| Klaus Tschira Stiftung: 2019-0-00079 |
|
Deposit Date
| 2025-02-10 |
|
Data Type
| Article |
|
Data Source
| Chemical Science; ISSN: 20416520, eISSN: 20416539, vol. 16, n° 8, pp. 3720-3737, 2025 |