Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution
This work addresses the computational barrier for MEP discovery in catalyst and biomolecular design, offering a promising incremental improvement for scientific applications.
The paper tackles the high computational cost of the nudged elastic band (NEB) method for finding minimum energy pathways by introducing Neural Network Bayesian Algorithm Execution (NN-BAX), which reduces energy and force evaluations by one to two orders of magnitude with negligible accuracy loss in tests on Lennard-Jones and Embedded Atom Method systems.
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.