Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations

TL;DR

This paper introduces bpopNN, a machine learning method that models DFT potential energy surfaces by incorporating electronic populations, enabling better handling of electronic state variations and environmental effects in molecular systems.

Contribution

The paper presents a novel ML approach that models DFT energies as a function of atomic electronic populations, integrating electronic structure information directly into the potential energy surface approximation.

Findings

bpopNN accurately models DFT PESs for Li clusters

The approach adapts to environmental electronic changes

It demonstrates improved flexibility over traditional ML PES methods

Abstract

Machine Learning (ML) approximations to Density Functional Theory (DFT) potential energy surfaces (PESs) are showing great promise for reducing the computational cost of accurate molecular simulations, but at present they are not applicable to varying electronic states, and in particular, they are not well suited for molecular systems in which the local electronic structure is sensitive to the medium to long-range electronic environment. With this issue as the focal point, we present a new Machine Learning approach called bpopNN for obtaining efficient approximations to DFT PESs. The methodology is based on approaching the true DFT energy as a function of electron populations on atoms, which may be realized in practice with constrained DFT (CDFT). The new approach creates approximations to this function with deep neural networks. These approximations thereby incorporate electronic information naturally into a ML approach, and optimizing the model energy with respect to populations allows the electronic terms to self-consistently adapt to the environment, as in DFT. We confirm the effectiveness of this approach with a variety of calculations on Li$_n$H$_n$ clusters.