Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning

TL;DR

The paper introduces Quantum Deep Field (QDF), a machine learning model that predicts molecular properties, electron densities, and atomization energies, demonstrating accurate predictions, valid density generation, and extrapolation capabilities.

Contribution

QDF is a novel physics-informed deep learning model that jointly predicts electron densities and molecular energies, advancing the integration of physics and machine learning in quantum chemistry.

Findings

QDF accurately predicts atomization energies.

QDF generates valid electron densities.

QDF demonstrates extrapolation beyond training data.

Abstract

Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn--Sham density functional theory (KS-DFT). Although this prediction is fast and accurate, we believe that a DNN model for KS-DFT must not only predict the properties but also provide the electron density of a molecule. This letter presents the quantum deep field (QDF), which provides the electron density with an unsupervised but end-to-end physics-informed modeling by learning the atomization energy on a large-scale dataset. QDF performed well at atomization energy prediction, generated valid electron density, and demonstrated extrapolation. Our QDF implementation is available at https://github.com/masashitsubaki/QuantumDeepField_molecule.