Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution

2025-03-23 · Moin Uddin Maruf, Sungmin Kim, Zeeshan Ahmad

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.

📄 PDF Abstract BibTeX arXiv:2503.17949

Code (1)

ahmad-research-group/nequip-charge 공식 구현 pytorch

An SO(3)-equivariant reciprocal-space neural potential for long-range interactions

2026-03-19 · Lingfeng Zhang, Taoyong Cui, Dongzhan Zhou, Lei Bai 외 arxiv

Long-range electrostatic and polarization interactions play a central role in molecular and condensed-phase systems, yet remain fundamentally incompatible with locality-based machine-learning interatomic potentials. Alth…

Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials

2026-03-24 · Shuyu Bi, Zhede Zhao, Qiangchao Sun, Tao Hu 외 arxiv

The core of molecular dynamics simulation fundamentally lies in the interatomic potential. Traditional empirical potentials lack accuracy, while first-principles methods are computationally prohibitive. Machine learning …

Computational Efficiency Graph Neural Network

E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials

2021-01-08 · Simon Batzner, Albert Musaelian, Lixin Sun, Mario Geiger 외

This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While…

Equivariant Evidential Deep Learning for Interatomic Potentials

2026-02-11 · Zhongyao Wang, Taoyong Cui, Jiawen Zou, Shufei Zhang 외 arxiv

Uncertainty quantification (UQ) is critical for assessing the reliability of machine learning interatomic potentials (MLIPs) in molecular dynamics (MD) simulations, identifying extrapolation regimes and enabling uncertai…

Active Learning

The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials

2022-05-13 · Ilyes Batatia, Simon Batzner, Dávid Péter Kovács, Albert Musaelian 외

The rapid progress of machine learning interatomic potentials over the past couple of years produced a number of new architectures. Particularly notable among these are the Atomic Cluster Expansion (ACE), which unified m…