Quantum-chemical insights from deep tensor neural networks

TLDR

Learning from data has spurred paradigm shifts in fields such as web, text, image search, speech recognition, and bioinformatics, raising the question of whether machine learning can similarly advance understanding of quantum many‑body systems. The study develops an efficient deep learning approach to provide spatially and chemically resolved insights into quantum‑mechanical observables of molecular systems. The authors unify many‑body Hamiltonian concepts with purpose‑designed deep tensor neural networks, achieving size‑extensive, uniformly accurate (≈1 kcal mol⁻¹) predictions across compositional and configurational chemical space for intermediate‑size molecules. The model classifies aromatic rings by stability and accurately predicts atomic energies, local chemical potentials, isomer energies, and identifies molecules with peculiar electronic structures, demonstrating machine learning’s potential to reveal insights into complex quantum‑chemical systems.

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, which leads to size-extensive and uniformly accurate (1 kcal mol-1) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the model reveals a classification of aromatic rings with respect to their stability. Further applications of our model for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the potential of machine learning for revealing insights into complex quantum-chemical systems.