Data Generation for Machine Learning Interatomic Potentials and Beyond
Top Cited Papers
Open Access
- 21 November 2024
- journal article
- review article
- Published by American Chemical Society (ACS) in Chemical Reviews
- Vol. 124 (24) , 13681-13714
Abstract
The field of data-driven chemistry is undergoing an evolution, driven by innovations in machine learning models for predicting molecular properties and behavior. Recent strides in ML-based interatomic potentials have paved the way for accurate modeling of diverse chemical and structural properties at the atomic level. The key determinant defining MLIP reliability remains the quality of the training data. A paramount challenge lies in constructing training sets that capture specific domains in the vast chemical and structural space. This Review navigates the intricate landscape of essential components and integrity of training data that ensure the extensibility and transferability of the resulting models. We delve into the details of active learning, discussing its various facets and implementations. We outline different types of uncertainty quantification applied to atomistic data acquisition and the correlations between estimated uncertainty and true error. The role of atomistic data samplers in generating diverse and informative structures is highlighted. Furthermore, we discuss data acquisition via modified and surrogate potential energy surfaces as an innovative approach to diversify training data. The Review also provides a list of publicly available data sets that cover essential domains of chemical space.Keywords
Funding Information
- Los Alamos National Laboratory
- Chemical Sciences, Geosciences, and Biosciences Division (89233218CNA000001)
- Basic Energy Sciences (LANLE8B3)
- Laboratory Directed Research and Development
This publication has 311 references indexed in Scilit:
- Transition Path Sampling as Markov Chain Monte Carlo of Trajectories: Recent Algorithms, Software, Applications, and Future OutlookAdvanced Theory and Simulations, 2021
- New parallel computing algorithm of molecular dynamics for extremely huge scale biological systemsJournal of Computational Chemistry, 2020
- Predicting Regioselectivity in Radical C−H Functionalization of Heterocycles through Machine LearningAngewandte Chemie, 2020
- Machine Learning Interatomic Potentials as Emerging Tools for Materials ScienceAdvanced Materials, 2019
- Noncovalent Carbon‐Bonding Interactions in ProteinsAngewandte Chemie International Edition, 2018
- molSimplify: A toolkit for automating discovery in inorganic chemistryJournal of Computational Chemistry, 2016
- Single‐ended transition state finding with the growing string methodJournal of Computational Chemistry, 2015
- NBO 6.0: Natural bond orbital analysis programJournal of Computational Chemistry, 2013
- Development and testing of a general amber force fieldJournal of Computational Chemistry, 2004
- Optimization of equilibrium geometries and transition structuresJournal of Computational Chemistry, 1982