Crash Testing Machine Learning Force Fields for Molecules, Materials, and Interfaces: Model Analysis in the TEA Challenge 2023
Authors:
- Igor PoltavskyIPIgor Poltavsky
- Anton Charkin-GorbulinACAnton Charkin-Gorbulin
- Mirela PulevaMPMirela Puleva
- Gregory Cordeiro FonsecaGFGregory Cordeiro Fonseca
- Ilyes BatatiaIBIlyes Batatia
- Nicholas J. BrowningNBNicholas J. Browning
- Stefan ChmielaSCStefan Chmiela
- Mengnan CuiMCMengnan Cui
- J. Thorben FrankJFJ. Thorben Frank
- Bing HuangBHBing Huang
- Silvan KäserSKSilvan Käser
Preprint
- 27 September 2024
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
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 (FF), 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*A) 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 MLFFs' ability 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.Keywords
All Related Versions
- Version 1, 2024-09-27, ChemRxiv
- Published version: Chemical Science, 16 (8), 3720.
This publication has 63 references indexed in Scilit:
- On the Origin of Energetic Disorder in Mixed Halides Lead PerovskitesAdvanced Optical Materials, 2023
- Equivariant Graph Neural Networks for Toxicity PredictionChemical Research in Toxicology, 2023
- Machine learned coarse-grained protein force-fields: Are we there yet?Current Opinion in Structural Biology, 2023
- Gaussian Process Regression for Materials and MoleculesChemical Reviews, 2021
- Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical SystemsChemical Reviews, 2021
- A study of adatom ripening on an Al (1 1 1) surface with machine learning force fieldsComputational Materials Science, 2017
- Modeling Molecular Interactions in Water: From Pairwise to Many-Body Potential Energy FunctionsChemical Reviews, 2016
- Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentialsJournal of Computational Physics, 2015
- TD-DFT benchmarks: A reviewInternational Journal of Quantum Chemistry, 2013
- Ab initio molecular simulations with numeric atom-centered orbitalsComputer Physics Communications, 2009