Crash Testing Machine Learning Force Fields for Molecules, Materials, and Interfaces: Molecular Dynamics in the TEA Challenge 2023
Authors:
- Igor PoltavskyIPIgor Poltavsky
- Mirela PulevaMPMirela Puleva
- Anton Charkin-GorbulinACAnton Charkin-Gorbulin
- 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
We present the second part of the rigorous evaluation of state-of-the-art machine learning force fields (MLFFs) within the TEA Challenge 2023. This study provides an in-depth analysis of the performance of MACE, SO3krates, sGDML, SOAP/GAP, and FCHL19* in modeling molecules, molecule-surface interfaces, and periodic materials. We compare observables obtained from molecular dynamics (MD) simulations using different MLFFs under identical conditions. Where applicable, density-functional theory (DFT) or experiment serves as a reference to reliably assess the performance of the machine learning models. In the absence of DFT benchmarks, we conduct a comparative analysis based on results from various MLFF architectures. Our findings indicate that at the current stage of MLFF development, the choice of the ML model is becoming less critical, as the resulting simulations are largely independent of the MLFF architecture. Instead, emphasis should be placed on developing complete, reliable, and representative training datasets. Nonetheless, long-range noncovalent interactions remain challenging for all MLFF models, necessitating special caution in simulations of physical systems where such interactions are prominent, such as molecule-surface interfaces. The findings presented here reflect the state of MLFF models as of October 2023.Keywords
All Related Versions
This publication has 57 references indexed in Scilit:
- On the Origin of Energetic Disorder in Mixed Halides Lead PerovskitesAdvanced Optical Materials, 2023
- Dynamic Local Structure in Caesium Lead Iodide: Spatial Correlation and Transient DomainsSmall, 2023
- Characterizing Uncertainty in Machine Learning for ChemistryJournal of Chemical Information and Modeling, 2023
- Linear Atomic Cluster Expansion Force Fields for Organic Molecules: Beyond RMSEJournal of Chemical Theory and Computation, 2021
- Gaussian Process Regression for Materials and MoleculesChemical Reviews, 2021
- Metrics for Benchmarking and Uncertainty Quantification: Quality, Applicability, and Best Practices for Machine Learning in ChemistryTrends in Chemistry, 2021
- ChemML: A machine learning and informatics program package for the analysis, mining, and modeling of chemical and materials dataWIREs Computational Molecular Science, 2020
- Vibrational Response of Methylammonium Lead Iodide: From Cation Dynamics to Phonon–Phonon InteractionsChemSusChem, 2016
- Stereochemical criteria for polypeptides and proteins. V. Conformation of a system of three linked peptide unitsBiopolymers, 1968
- Stereochemistry of polypeptide chain configurationsJournal of Molecular Biology, 1963