On the practical applicability of modern DFT functionals for chemical computations. Case study of DM21 applicability for geometry optimization

TL;DR

This paper evaluates the practical use of the DM21 neural network-based DFT functional for molecular geometry optimization, comparing its performance with traditional functionals and addressing challenges for broader applicability.

Contribution

It introduces an implementation of DM21 in geometry optimization, compares its performance with traditional functionals, and proposes solutions to improve its practical applicability.

Findings

DM21 shows potential for geometry optimization in DFT.

Challenges include oscillatory behavior affecting accuracy.

Proposed solutions extend DM21's applicability to new substances.

Abstract

Density functional theory (DFT) is probably the most promising approach for quantum chemistry calculations considering its good balance between calculations precision and speed. In recent years, several neural network-based functionals have been developed for exchange-correlation energy approximation in DFT, DM21 developed by Google Deepmind being the most notable between them. This study focuses on evaluating the efficiency of DM21 functional in predicting molecular geometries, with a focus on the influence of oscillatory behavior in neural network exchange-correlation functionals. We implemented geometry optimization in PySCF for the DM21 functional in geometry optimization problem, compared its performance with traditional functionals, and tested it on various benchmarks. Our findings reveal both the potential and the current challenges of using neural network functionals for geometry optimization in DFT. We propose a solution extending the practical applicability of such functionals and allowing to model new substances with their help.