Machine Learning Inference of Molecular Dipole Moment in Liquid Water

TL;DR

This paper introduces a data-driven, physically constrained machine learning approach to infer molecular dipole moments in liquid water, offering insights comparable to traditional Wannier function methods and emphasizing interpretability improvements.

Contribution

It presents a novel graph convolution-based charge model that incorporates physical constraints to accurately infer molecular dipole moments in liquid water.

Findings

Distribution of inferred dipole moments aligns with Wannier function results

Physical constraints improve model interpretability

Machine learning offers a maximum-likelihood alternative to established methods

Abstract

Molecular dipole moment in liquid water is an intriguing property, partly due to the fact that there is no unique way to partition the total electron density into individual molecular contributions. The prevailing method to circumvent this problem is to use maximally localized Wannier functions, which perform a unitary transformation of the occupied molecular orbitals by minimizing the spread function of Boys. Here we revisit this problem using a data-driven approach satisfying two physical constraints, namely: i) The displacement of the atomic charges is proportional to the Berry phase polarization; ii) Each water molecule has a formal charge of zero. It turns out that the distribution of molecular dipole moments in liquid water inferred from latent variables is surprisingly similar to that obtained from maximally localized Wannier functions. Apart from putting a maximum-likelihood footnote to the established method, this work highlights the capability of graph convolution based charge models and the importance of physical constraints on improving the interpretability.