Implicit Neural Representations for Chemical Reaction Paths

TL;DR

This paper introduces a neural network-based method for representing chemical reaction paths continuously, providing advantages over traditional discrete methods like NEB, especially in complex or multi-step reactions.

Contribution

The authors develop a neural network approach to model reaction paths that can handle complex scenarios and generalize across systems, surpassing existing discrete path-search methods.

Findings

Neural networks can accurately represent minimum energy paths.

The method outperforms NEB in complex atomistic systems.

A single network can learn and generalize reaction paths.

Abstract

We show that neural networks can be optimized to represent minimum energy paths as continuous functions, offering a flexible alternative to discrete path-search methods such as Nudged Elastic Band (NEB). Our approach parameterizes reaction paths with a network trained on a loss function that discards tangential energy gradients and enables instant estimation of the transition state. We first validate the method on two-dimensional potentials and then demonstrate its advantages over NEB on challenging atomistic systems where (i) poor initial guesses yield unphysical paths, (ii) multiple competing paths exist, or (iii) the reaction follows a complex multi-step mechanism. Results highlight the versatility of the method: for instance, a simple adjustment to the sampling strategy during optimization can help escape local-minimum solutions. Finally, in a low-dimensional setting, we demonstrate that a single neural network can learn from existing paths and generalize to unseen systems, showing promise for a universal reaction path representation.