Crash testing machine learning force fields for molecules, materials, and interfaces: model analysis in the TEA Challenge 2023

Title data

Poltavsky, Igor ; Charkin-Gorbulin, Anton ; Puleva, Mirela ; Fonseca, Grégory ; Batatia, Ilyes ; Browning, Nicholas J. ; Chmiela, Stefan ; Cui, Mengnan ; Frank, J. Thorben ; Heinen, Stefan ; Huang, Bing ; Käser, Silvan ; Kabylda, Adil ; Khan, Danish ; Müller, Carolin ; Price, Alastair J. A. ; Riedmiller, Kai ; Töpfer, Kai ; Ko, Tsz Wai ; Meuwly, Markus ; Rupp, Matthias ; Csányi, Gábor ; von Lilienfeld, O. Anatole ; Margraf, Johannes T. ; Müller, Klaus-Robert ; Tkatchenko, Alexandre:
Crash testing machine learning force fields for molecules, materials, and interfaces: model analysis in the TEA Challenge 2023.
In: Chemical Science. Vol. 16 (2025) . - pp. 3720-3737.
ISSN 2041-6539
DOI: https://doi.org/10.1039/D4SC06529H

Official URL:

Abstract in another language

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.

Further data

Item Type:	Article in a journal
Refereed:	Yes
Institutions of the University:	Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Chemistry > Chair Physical Chemistry V - Theory and Machine Learning Faculties > Faculty of Biology, Chemistry and Earth Sciences > Department of Chemistry > Chair Physical Chemistry V - Theory and Machine Learning > Chair Physical Chemistry V - Theory and Machine Learning - Univ.-Prof. Dr. Johannes Theo Margraf
Result of work at the UBT:	Yes
DDC Subjects:	500 Science > 540 Chemistry
Date Deposited:	31 Mar 2025 06:14
Last Modified:	31 Mar 2025 06:14
URI:	https://eref.uni-bayreuth.de/id/eprint/93052