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

Igor Poltavsky; Anton Charkin-Gorbulin; Mirela Puleva; Grégory Fonseca; Ilyes Batatia; Nicholas J. Browning; Stefan Chmiela; Mengnan Cui; J. Thorben Frank; Stefan Heinen; Bing Huang; Silvan Käser; Adil Kabylda; Danish Khan; Carolin Müller; Alastair J. A. Price; Kai Riedmiller; Kai Töpfer; Tsz Wai Ko; Markus Meuwly; Matthias Rupp; Gábor Csányi; O. Anatole von Lilienfeld; Johannes T. Margraf; Klaus-Robert Müller; Alexandre Tkatchenko

doi:10.1039/D4SC06529H

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

Igor Poltavsky,

*^a Anton Charkin-Gorbulin,‡^ab Mirela Puleva,‡^ac Grégory Fonseca,‡^a Ilyes Batatia,^d Nicholas J. Browning,^e Stefan Chmiela,^fg Mengnan Cui,^h J. Thorben Frank,

^fg Stefan Heinen,ⁱ Bing Huang,^j Silvan Käser,

^k Adil Kabylda,

^a Danish Khan,^il Carolin Müller,

^m Alastair J. A. Price,^no Kai Riedmiller,

^p Kai Töpfer,

^k Tsz Wai Ko,^q Markus Meuwly,

^k Matthias Rupp,

^r Gábor Csányi,

^d O. Anatole von Lilienfeld,

^fginost Johannes T. Margraf,^u Klaus-Robert Müller

^fgvwx and Alexandre Tkatchenko

*^ac

Author affiliations

* Corresponding authors

^a Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg, Luxembourg
E-mail: alexandre.tkatchenko@uni.lu, igor.poltavskyi@uni.lu

^b Laboratory for Chemistry of Novel Materials, University of Mons, B-7000 Mons, Belgium

^c Institute for Advanced Studies, University of Luxembourg, Campus Belval, L-4365 Esch-sur-Alzette, Luxembourg

^d Department of Engineering, University of Cambridge, Trumpington Street, Cambridge, UK

^e Swiss National Supercomputing Centre (CSCS), 6900 Lugano, Switzerland

^f Machine Learning Group, Technical University Berlin, Berlin, Germany

^g BIFOLD, Berlin Institute for the Foundations of Learning and Data, Berlin, Germany

^h Fritz-Haber-Institut der Max-Planck-Gesellschaft, Berlin, Germany

ⁱ Vector Institute for Artificial Intelligence, Toronto, ON, Canada

^j Wuhan University, Department of Chemistry and Molecular Sciences, 430072 Wuhan, China

^k Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland

^l Chemical Physics Theory Group, Department of Chemistry, University of Toronto, St George Campus, Toronto, ON, Canada

^m Friedrich-Alexander-Universität Erlangen-Nürnberg, Computer-Chemistry-Center, Nägelsbachstraße 25, 91052 Erlangen, Germany

ⁿ Department of Chemistry, University of Toronto, St George Campus, Toronto, ON, Canada

^o Acceleration Consortium, University of Toronto, 80 St George St, Toronto, ON M5S 3H6, Canada

^p Heidelberg Institute for Theoretical Studies, Heidelberg, Germany

^q Department of NanoEngineering, University of California San Diego, 9500 Gilman Dr, Mail Code 0448, La Jolla, CA 92093-0448, USA

^r Luxembourg Institute of Science and Technology (LIST), L-4362 Esch-sur-Alzette, Luxembourg

^s Department of Materials Science and Engineering, University of Toronto, St George Campus, Toronto, ON, Canada

^t Department of Physics, University of Toronto, St George Campus, Toronto, ON, Canada

^u University of Bayreuth, Bavarian Center for Battery Technology (BayBatt), Bayreuth, Germany

^v Department of Artificial Intelligence, Korea University, Seoul, South Korea

^w Max Planck Institut für Informatik, Saarbrücken, Germany

^x Google DeepMind, Berlin, Germany

Abstract

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.

Chemical Science

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

Abstract

Supplementary files

Article information

Download Citation

Permissions

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

Social activity

Search articles by author

Spotlight

Advertisements