Enhancing molecular dynamics with equivariant machine-learned densities
For computational chemists and materials scientists, DenSNet provides a unified framework for molecular dynamics and electronic structure prediction, overcoming the limitation of traditional MLIPs that only predict energies and forces.
DenSNet learns the Hohenberg-Kohn map from nuclear configurations to ground-state electron density using an SE(3)-equivariant neural network, enabling molecular dynamics with electronic observables. It achieves excellent agreement with experimental infrared spectra for ethanol, ethanethiol, and resorcinol, and scales to polythiophene oligomers with up to 12 monomers.
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 $Δ$-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.