SchNet - A deep learning architecture for molecules and materials

K T Schütt; H E Sauceda; P-J Kindermans; A Tkatchenko; K-R Müller

doi:10.1063/1.5019779

SchNet - A deep learning architecture for molecules and materials

J Chem Phys. 2018 Jun 28;148(24):241722. doi: 10.1063/1.5019779.

Authors

K T Schütt¹, H E Sauceda², P-J Kindermans¹, A Tkatchenko³, K-R Müller¹

Affiliations

¹ Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany.
² Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany.
³ Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg.

PMID: 29960322
DOI: 10.1063/1.5019779

Abstract

Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C₂₀-fullerene that would have been infeasible with regular ab initio molecular dynamics.