Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution

TL;DR

This paper presents NN-BAX, a neural network Bayesian framework that significantly reduces computational costs in discovering minimum energy pathways, enabling faster and scalable analysis of complex systems with minimal accuracy loss.

Contribution

The paper introduces NN-BAX, a novel active learning framework that jointly learns energy landscapes and MEPs, drastically reducing computational effort compared to traditional methods.

Findings

Achieves 10-100x reduction in energy and force evaluations.

Maintains negligible loss in MEP accuracy.

Scales effectively to systems with over 100 dimensions.

Abstract

The discovery of a minimum energy pathway (MEP) between metastable states is crucial for scientific tasks including catalyst and biomolecular design. However, the standard nudged elastic band (NEB) algorithm requires hundreds to tens of thousands of compute-intensive simulations, making applications to complex systems prohibitively expensive. We introduce Neural Network Bayesian Algorithm Execution (NN-BAX), a framework that jointly learns the energy landscape and the MEP. NN-BAX sequentially fine-tunes a foundation model by actively selecting samples targeted at improving the MEP. Tested on Lennard-Jones and Embedded Atom Method systems, our approach achieves a one to two order of magnitude reduction in energy and force evaluations with negligible loss in MEP accuracy and demonstrates scalability to >100-dimensional systems. This work is therefore a promising step towards removing the computational barrier for MEP discovery in scientifically relevant systems, suggesting that weeks-long calculations may be achieved in hours or days with minimal loss in accuracy.