Active Learning of Neural Network Potentials for Rare Events
Preprint
- 13 August 2023
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Atomistic simulation with machine learning-based potentials (MLPs) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside their training domain and often fail catastrophically in predicting rare events in molecular dynamics (MD) simulations. The rare events in atomistic modeling typically include chemical bond breaking/formation, phase transitions, and materials failure, which are critical for new materials design, synthesis, and manufacturing processes. In this study, we develop an automated active learning (AL) capability by combining NNPs and enhanced sampling methods for capturing rare events to derive NNPs for targeted applications. We develop a decision engine based on configurational similarity and uncertainty quantification (UQ), using data augmentation for effective AL loops to distinguish the informative data from enhanced sampled configurations, showing that the generated data set achieves an activation energy error of less than 1 kcal/mol. Furthermore, we have devised a strategy to alleviate training uncertainty within AL iterations through a carefully constructed data selection process that leverages an ensemble approach. Our study provides essential insight into the relationship between data and the performance of NNP for the rare event of bond breaking under mechanical loading. It highlights strategies for developing NNPs of broader materials and applications through active learning.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Dynamic aspects of graphene deformation and fracture from approximate density functional theoryCarbon, 2022
- Atomistic Mechanics of Torn Back Folded Edges of Triangular Voids in Monolayer WS2Small, 2021
- Active learning accelerates ab initio molecular dynamics on reactive energy surfacesChem, 2021
- Machine learning: Accelerating materials development for energy storage and conversionInfoMat, 2020
- Multiscale modeling of keratin, collagen, elastin and related human diseases: Perspectives from atomistic to coarse-grained molecular dynamics simulationsExtreme Mechanics Letters, 2018
- Enhanced sampling techniques in molecular dynamics simulations of biological systemsBiochimica et Biophysica Acta (BBA) - General Subjects, 2015
- Adaptive machine learning framework to accelerate ab initio molecular dynamicsInternational Journal of Quantum Chemistry, 2014
- Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networksChemical Physics Letters, 2004
- Molecular dynamics study of unbinding of the avidin-biotin complexBiophysical Journal, 1997
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995