Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces

TL;DR

This paper introduces FBGNN-MBE, a novel computational framework combining graph neural networks with many-body expansion theory to accurately predict potential energy surfaces of large chemical systems, enabling scalable material design.

Contribution

The study develops and demonstrates a new method integrating deep learning with fragment-based quantum mechanics for efficient potential energy surface prediction.

Findings

Successfully reproduces full-dimensional potential energy surfaces.

Manages complexity and interpretability in large systems.

Shows promise for computational design of functional materials.

Abstract

Rational design of next-generation functional materials relied on quantitative predictions of their electronic structures beyond single building blocks. First-principles quantum mechanical (QM) modeling became infeasible as the size of a material grew beyond hundreds of atoms. In this study, we developed a new computational tool integrating fragment-based graph neural networks (FBGNN) into the fragment-based many-body expansion (MBE) theory, referred to as FBGNN-MBE, and demonstrated its capacity to reproduce full-dimensional potential energy surfaces (FD-PES) for hierarchic chemical systems with manageable accuracy, complexity, and interpretability. In particular, we divided the entire system into basic building blocks (fragments), evaluated their single-fragment energies using a first-principles QM model and attacked many-fragment interactions using the structure-property relationships trained by FBGNNs. Our development of FBGNN-MBE demonstrated the potential of a new framework integrating deep learning models into fragment-based QM methods, and marked a significant step towards computationally aided design of large functional materials.