A large language model-type architecture for high-dimensional molecular potential energy surfaces

TL;DR

This paper introduces a graph-based neural network algorithm inspired by large language models to accurately predict high-dimensional molecular potential energy surfaces, achieving near chemical accuracy for complex systems.

Contribution

It presents a novel neural network approach that generalizes from lower to higher-dimensional molecular systems, enabling accurate full-dimensional potential energy surface predictions.

Findings

Achieved sub-kcal/mol accuracy for 51 nuclear dimensions.

Successfully extended the method to 186 dimensions, including a 21-water cluster.

Produced the first full-dimensional potential energy surface for this cluster at CCSD level.

Abstract

Computing high-dimensional potential energy surfaces for molecular systems and materials is considered to be a great challenge in computational chemistry with potential impact in a range of areas including the fundamental prediction of reaction rates. In this paper, we design and discuss an algorithm that has similarities to large language models in generative AI and natural language processing. Specifically, we represent a molecular system as a graph which contains a set of nodes, edges, faces, etc. Interactions between these sets, which represent molecular subsystems in our case, are used to construct the potential energy surface for a reasonably sized chemical system with 51 nuclear dimensions. For this purpose, a family of neural networks that pertain to the graph-theoretically obtained subsystems get the job done for this 51 nuclear dimensional system. We then ask if this same family of lower-dimensional graph-based neural networks can be transformed to provide accurate predictions for a 186-dimensional potential energy surface. We find that our algorithm does provide accurate results for this larger-dimensional problem with sub-kcal/mol accuracy for the higher-dimensional potential energy surface problem. Indeed, as a result of these developments, here we produce the first efforts towards a full-dimensional potential energy surface for the protonated 21-water cluster (186 nuclear dimensions) at CCSD level accuracy.