Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics

Abstract

Accurate modeling of chemically reactive systems has traditionally relied on either expensive ab initio approaches or flexible bond-order force fields such as ReaxFF that require considerable time, effort, and expertise to parameterize. Here, we introduce FLARE++, a Bayesian active learning method for training reactive many-body force fields on the fly during molecular dynamics (MD) simulations. During the automated training loop, the predictive uncertainties of a sparse Gaussian process (SGP) force field are evaluated at each timestep of an MD simulation to determine whether additional ab initio data are needed. Once trained, the SGP is mapped onto an equivalent and much faster model that is polynomial in the local environment descriptors and whose prediction cost is independent of the training set size. We apply our method to a canonical reactive system in the field of heterogeneous catalysis, hydrogen splitting and recombination on a platinum (111) surface, obtaining a trained model within three days of wall time that is twice as fast as a recent Pt/H ReaxFF force field and considerably more accurate. Our method is fully open source and is expected to reduce the time and effort required to train fast and accurate reactive force fields for complex systems.

References in corpus (4)

• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• On-the-fly machine learning force field generation: Application to melting points
• Machine-learning based interatomic potential for amorphous carbon
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference

Cited by in corpus (19)

• A practical guide to machine learning interatomic potentials -- Status and future
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• A reactive neural network framework for water-loaded acidic zeolites
• Effect of cation-disorder on lithium transport in halide superionic conductors
• Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension
• Room-temperature decomposition of the ethaline deep eutectic solvent
• Phase transitions of LaMnO${}_3$ and SrRuO${}_3$ from DFT + U based machine learning force fields simulations
• Accelerated Bayesian Inference for Molecular Simulations using Local Gaussian Process Surrogate Models
• A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements
• Efficient ensemble uncertainty estimation in Gaussian Processes Regression
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
• A Planning-and-Exploring Approach to Extreme-Mechanics Force Fields
• Evolutionary Monte Carlo of QM properties in chemical space: Electrolyte design
• Machine-Learning-Guided Insights into Solid-Electrolyte Interphase Conductivity: Are Amorphous Lithium Fluorophosphates the Key?
• k-Means Clustering in Fingerprint-Based Configuration Selection for Fitting Interatomic Potentials
• Considerations in the use of ML interaction potentials for free energy calculations
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation
• FreeBird.jl: An Extensible Toolbox for Simulating Interfacial Phase Equilibria