🤖 AI Summary
This work addresses the slow convergence of traditional self-consistent field (SCF) calculations caused by poor initial guesses. The authors propose an end-to-end approach based on the equivariant PhiSNet architecture that directly predicts the one-electron reduced density matrix (1-RDM) in an atomic orbital basis from molecular geometry. Physical constraints—such as electron number conservation and generalized idempotency—are enforced through a lightweight analytical module, enabling the simultaneous generation of high-quality SCF initial guesses, total energies, and Hellmann–Feynman forces without explicit force supervision. Evaluated on six closed-shell molecules, the method reduces SCF iteration counts by 49%–81%, substantially accelerating convergence while maintaining high accuracy.
📝 Abstract
We present \textsc{dm-PhiSNet}, a physically constrained \textsc{PhiSNet}-based equivariant model that predicts one-electron reduced density matrices (1-RDMs) directly from molecular geometries in an atomic-orbital (AO) basis for accelerated self-consistent field (SCF) workflows. Training follows a two-stage schedule with progressively introduced physically motivated objectives, and the resulting predictions are refined by a lightweight analytic block. This block enforces electron-number conservation, drives the 1-RDM toward generalized idempotency in the AO metric, and regularizes the occupation spectrum of the Löwdin-orthogonalized density. Across six closed-shell systems -- H$_2$O, CH$_4$, NH$_3$, HF, ethanol, and NO$_3^-$ -- the refined 1-RDMs provide SCF initial guesses that substantially reduce iteration steps by 49--81\% relative to standard initializations. Beyond SCF acceleration, the learned 1-RDMs yield accurate one-shot total energies and Hellmann--Feynman atomic forces without force supervision, indicating that the model captures chemically meaningful electronic structure. These results demonstrate that combining equivariant learning with analytic constraint enforcement provides a simple, general route to solver-ready density-matrix initializations and accelerated SCF workflows.