The Many-Body Expansion Combined with Neural Networks

TL;DR

This paper explores combining many-body expansion (MBE) with neural networks (NNs) to efficiently model large chemical systems, achieving ab-initio accuracy with significantly reduced computational cost and enhanced generality.

Contribution

It demonstrates the synergy of MBE and NNs, showing NNs can drastically reduce computational overhead while maintaining accuracy, and introduces a new chemical embedding for property prediction.

Findings

NNs reduce MBE computational cost by over 10^6 times.

The combined approach achieves ab-initio accuracy efficiently.

A new chemical embedding enables inverse property prediction.

Abstract

Fragmentation methods such as the many-body expansion (MBE) are a common strategy to model large systems by partitioning energies into a hierarchy of decreasingly significant contributions. The number of fragments required for chemical accuracy is still prohibitively expensive for ab-initio MBE to compete with force field approximations for applications beyond single-point energies. Alongside the MBE, empirical models of ab-initio potential energy surfaces have improved, especially non-linear models based on neural networks (NN) which can reproduce ab-initio potential energy surfaces rapidly and accurately. Although they are fast, NNs suffer from their own curse of dimensionality; they must be trained on a representative sample of chemical space. In this paper we examine the synergy of the MBE and NN's, and explore their complementarity. The MBE offers a systematic way to treat systems of arbitrary size and intelligently sample chemical space. NN's reduce, by a factor in excess of $10^6$ the computational overhead of the MBE and reproduce the accuracy of ab-initio calculations without specialized force fields. We show they are remarkably general, providing comparable accuracy with drastically different chemical embeddings. To assess this we test a new chemical embedding which can be inverted to predict molecules with desired properties.