Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

TL;DR

This paper introduces a scalable, physically-informed deep learning model for Kohn-Sham Hamiltonians in DFT, significantly improving accuracy and speed for large molecular systems.

Contribution

The study develops a new loss function, WALoss, and a larger training dataset to enhance the scalability and physical accuracy of neural network models for DFT calculations.

Findings

Reduced total energy prediction error by a factor of 1347

Achieved an 18% speed-up in SCF DFT calculations

Set new benchmarks for large molecular system predictions

Abstract

Density Functional Theory (DFT) is a pivotal method within quantum chemistry and materials science, with its core involving the construction and solution of the Kohn-Sham Hamiltonian. Despite its importance, the application of DFT is frequently limited by the substantial computational resources required to construct the Kohn-Sham Hamiltonian. In response to these limitations, current research has employed deep-learning models to efficiently predict molecular and solid Hamiltonians, with roto-translational symmetries encoded in their neural networks. However, the scalability of prior models may be problematic when applied to large molecules, resulting in non-physical predictions of ground-state properties. In this study, we generate a substantially larger training set (PubChemQH) than used previously and use it to create a scalable model for DFT calculations with physical accuracy. For our model, we introduce a loss function derived from physical principles, which we call Wavefunction Alignment Loss (WALoss). WALoss involves performing a basis change on the predicted Hamiltonian to align it with the observed one; thus, the resulting differences can serve as a surrogate for orbital energy differences, allowing models to make better predictions for molecular orbitals and total energies than previously possible. WALoss also substantially accelerates self-consistent-field (SCF) DFT calculations. Here, we show it achieves a reduction in total energy prediction error by a factor of 1347 and an SCF calculation speed-up by a factor of 18%. These substantial improvements set new benchmarks for achieving accurate and applicable predictions in larger molecular systems.