# On-the-Fly Active Learning of Interpretable Bayesian Force Fields for Atomistic Rare Events

## TL;DR

This paper introduces an adaptive Bayesian active learning approach for training interpretable, low-dimensional interatomic force fields on the fly, significantly improving efficiency and accuracy in modeling rare events in atomistic simulations.

## Contribution

The authors develop an automated, active learning framework that uses Bayesian inference to efficiently train interpretable force fields with minimal ab initio data, enabling better modeling of rare events.

## Key findings

- Achieves a good balance of accuracy and efficiency in various systems.
- Requires minimal initial training data.
- Provides open-source implementation and a mapping procedure to tabulated force fields.

## Abstract

Machine learned force fields typically require manual construction of training sets consisting of thousands of first principles calculations, which can result in low training efficiency and unpredictable errors when applied to structures not represented in the training set of the model. This severely limits the practical application of these models in systems with dynamics governed by important rare events, such as chemical reactions and diffusion. We present an adaptive Bayesian inference method for automating the training of interpretable, low-dimensional, and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics simulations. Within an active learning framework, the internal uncertainty of a Gaussian process regression model is used to decide whether to accept the model prediction or to perform a first principles calculation to augment the training set of the model. The method is applied to a range of single- and multi-element systems and shown to achieve a favorable balance of accuracy and computational efficiency, while requiring a minimal amount of ab initio training data. We provide a fully open-source implementation of our method, as well as a procedure to map trained models to computationally efficient tabulated force fields.