Machine Learning Inference of Molecular Dipole Moment in Liquid Water

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.

References in corpus (10)

• Canonical sampling through velocity-rescaling
• Separable Dual Space Gaussian Pseudo-potentials
• Maximally-localized generalized Wannier functions for composite energy bands
• Machine Learning Unifies the Modelling of Materials and Molecules
• The Quantum-Mechanical Position Operator in Extended Systems
• A beginner's guide to the modern theory of polarization
• How van der Waals interactions determine the unique properties of water
• Deep neural network for the dielectric response of insulators
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials

Cited by in corpus (3)

• PiNNwall: Heterogeneous Electrode Models from Integrating Machine Learning and Atomistic Simulation
• Prediction of the morphological evolution of a splashing drop using an encoder-decoder
• Molecular electrostatic potentials from machine learning models for dipole and quadrupole predictions