Voltage-embedded equivariant machine learning potential for open system simulations
Abstract
Modeling electrochemical interfaces under operational non-equilibrium conditions is vital for energy technologies but remains bottlenecked by the expensive cost of ab initio methods. Current machine learning potentials, largely designed for closed systems under homogeneous electric fields, are limited in open quantum transport applications. To overcome this, we present an E(3)-equivariant graph neural network that embeds voltage bias for open-system simulations. Our approach decouples the system energy and forces into zero-bias and bias-dependent contributions, assigning distinct vector encodings to electrode and scattering-region atoms to capture non-equilibrium conditions. Trained on limited discrete bias data, the model achieves high predictive accuracy and robust extrapolation transferability. When applied to a lithium/water interface, our model successfully captures the field-induced dynamic reorientation of water molecules and reproduces asymmetric electrochemical behavior at different electrodes.
Related
- Realistic Simulations of Energy Materials Using Foundation Models and Electrode-Potential Learning
- Concerted, Facile CO2 Hydrogenation in Ni-MOF-74 Revealed by Machine Learning Interatomic Potential-Based Enhanced Sampling Simulations
- Embedded Morgan Fingerprints for more efficient molecular property predictions with machine learning
- Simulating enzyme catalysis with electrostatically embedded machine learning potentials
- BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
BibTeX
@misc{guan2026voltageembedded,
title = {{Voltage-embedded equivariant machine learning potential for open system simulations}},
author = {Yiming Guan and Rongzhi Gao and ChiYung Yam and GuanHua Chen and Ziyang Hu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04696},
eprint = {2609.04696},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04696},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Voltage-embedded equivariant machine learning potential for open system simulations
AU - Yiming Guan
AU - Rongzhi Gao
AU - ChiYung Yam
AU - GuanHua Chen
AU - Ziyang Hu
PY - 2026
DA - 2026/09/04
PB - arXiv
DO - 10.48550/arxiv.2609.04696
UR - https://arxiv.org/abs/2609.04696
AB - Modeling electrochemical interfaces under operational non-equilibrium conditions is vital for energy technologies but remains bottlenecked by the expensive cost of ab initio methods. Current machine learning potentials, largely designed for closed systems under homogeneous electric fields, are limited in open quantum transport applications. To overcome this, we present an E(3)-equivariant graph neural network that embeds voltage bias for open-system simulations. Our approach decouples the system energy and forces into zero-bias and bias-dependent contributions, assigning distinct vector encodings to electrode and scattering-region atoms to capture non-equilibrium conditions. Trained on limited discrete bias data, the model achieves high predictive accuracy and robust extrapolation transferability. When applied to a lithium/water interface, our model successfully captures the field-induced dynamic reorientation of water molecules and reproduces asymmetric electrochemical behavior at different electrodes.
ER -