Enhancing molecular dynamics with equivariant machine-learned densities

TL;DR

This paper introduces DenSNet, a novel equivariant neural network framework that predicts electron densities and energies from molecular configurations, enabling accurate molecular dynamics and electronic property predictions.

Contribution

DenSNet is the first density-first machine learning approach that maps nuclear configurations directly to electron densities and energies, improving transferability and electronic observable predictions.

Findings

Accurately predicts infrared spectra of molecules matching experimental data.

Successfully extrapolates to larger molecular chains with stable long-time trajectories.

Reinstates electron density as a central quantity for transferable electronic property prediction.

Abstract

Machine-learning interatomic potentials (MLIPs) have enabled molecular dynamics at near ab initio accuracy, yet remain limited to energies and forces by construction, leaving electronic observables such as dipole moments and polarizabilities inaccessible. We introduce DenSNet, a density-first approach to machine-learned electronic structure that learns the Hohenberg--Kohn map from nuclear configurations to the ground-state electron density. Our approach employs an SE(3)-equivariant neural network to predict density coefficients of a flexible atom-centered Gaussian basis, combined with a $\Delta$-learning strategy that uses superposed atomic densities as a prior to accelerate training. A second equivariant network then maps the predicted density to the total energy, providing a unified framework for molecular dynamics and electronic structure. We validate DenSNet on ethanol, ethanethiol, and resorcinol, where infrared spectra from machine-learned trajectories show excellent agreement with experimental gas-phase measurements. To test scalability, we train on polythiophene oligomers with 1--6 monomers and extrapolate to chains of up to 12 monomers, generating stable long-time trajectories whose infrared spectra agree with reference density functional theory calculations. Here, we show that reinstating the electron density as the central learned quantity opens a practical route to transferable prediction of spectroscopic and electronic observables in large-scale molecular simulations.