Quantum-Chemical Insights from Deep Tensor Neural Networks

TL;DR

This paper introduces a deep tensor neural network approach that provides accurate, spatially and chemically resolved predictions of quantum-mechanical properties in molecules, revealing new chemical insights.

Contribution

The authors develop a size-extensive deep tensor neural network that unifies many-body Hamiltonians with machine learning for quantum chemistry applications.

Findings

Achieves 1 kcal/mol accuracy across chemical space.

Classifies aromatic rings by stability, not in training data.

Predicts atomic energies and local potentials reliably.

Abstract

Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text, and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks (DTNN), which leads to size-extensive and uniformly accurate (1 kcal/mol) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the DTNN model reveals a classification of aromatic rings with respect to their stability -- a useful property that is not contained as such in the training dataset. Further applications of DTNN for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the high potential of machine learning for revealing novel insights into complex quantum-chemical systems.