Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution

Abstract

Machine learning interatomic potentials (MLIPs) provide a computationally efficient alternative to quantum mechanical simulations for predicting material properties. Message-passing graph neural networks, commonly used in these MLIPs, rely on local descriptor-based symmetry functions to model atomic interactions. However, such local descriptor-based approaches struggle with systems exhibiting long-range interactions, charge transfer, and compositional heterogeneity. In this work, we develop a new equivariant MLIP incorporating long-range Coulomb interactions through explicit treatment of electronic degrees of freedom, specifically global charge distribution within the system. This is achieved using a charge equilibration scheme based on predicted atomic electronegativities. We systematically evaluate our model across a range of benchmark periodic and non-periodic datasets, demonstrating that it outperforms both short-range equivariant and long-range invariant MLIPs in energy and force predictions. Our approach enables more accurate and efficient simulations of systems with long-range interactions and charge heterogeneity, expanding the applicability of MLIPs in computational materials science.

24 pages, 5 figures, 1 table + 12 pages of Supporting Information

References in corpus (18)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Advanced capabilities for materials modelling with Quantum ESPRESSO
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• A deep potential model with long-range electrostatic interactions
• Incorporating long-range physics in atomic-scale machine learning
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Accelerating computational materials discovery with artificial intelligence and cloud high-performance computing: from large-scale screening to experimental validation
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Interplay of local hydrogen-bonding and long-ranged dipolar forces in simulations of confined water
• Dielectric response with short-ranged electrostatics
• The effect of ionization on the global minima of small and medium sized silicon and magnesium clusters
• Machine Learning Enabled Discovery of Application Dependent Design Principles for Two-dimensional Materials
• Heterogeneity in Point Defect Distribution and Mobility in Solid Ion Conductors
• Modulation of Point Defect Properties Near Surfaces in Metal Halide Perovskites
• A foundation machine learning potential with polarizable long-range interactions for materials modelling
• Learning charges and long-range interactions from energies and forces