Differentiable Electronic Grand Canonical Learning for Electrochemistry
Abstract
Electronic grand-canonical density functional theory captures how structure and electronic charge respond to electrode potential and, together with statistical mechanics, how these responses give rise to emergent phenomena. However, its computational cost limits the system sizes and sampling times accessible to first- principles simulations. Here, we introduce a differentiable architecture that represents the grand potential and obtains forces and electronic charge as its derivatives, exactly satisfying the mixed-derivative constraints required for thermodynamic consistency, and implement it within the equivariant MACE framework as GC- MACE. We demonstrate more accurate joint learning across multiple electrochemical interfaces and improved transferability to thicker water films relative to previous models, while enabling constant-potential simulations at substantially larger length and time scales than accessible to ab initio molecular dynamics. With broad training data, the framework offers a route to thermodynamically consistent foundation interatomic potentials for the electronic grand canonical ensemble
Related
- Grand-Canonical DFT Study of Hydrogen Peroxide Electro-Reduction: The Effect of Sn Alloying on Pt and Pd Activity
- Solubility of poorly soluble species in bulk and nanopores from grand-canonical Wang-Landau sampling
- Grand-canonical DFT applied to the electro-oxidation of 5-hydroxymethylfurfural on (substituted) NiOOH(0001)
- Isotope Effects at Classical Cost through Mass-Differentiable Machine Learning
- Tetrathiafulvalene and π-extended tetrathiafulvalene pillar[5]arene conjugates: synthesis, electrochemistry and host–guest properties
BibTeX
@misc{pope2026differentiable,
title = {{Differentiable Electronic Grand Canonical Learning for Electrochemistry}},
author = {Phillip E. Pope and Timothy C. Berkelbach and Venkat Kapil},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40338},
eprint = {2610.40338},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40338},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Differentiable Electronic Grand Canonical Learning for Electrochemistry
AU - Phillip E. Pope
AU - Timothy C. Berkelbach
AU - Venkat Kapil
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40338
UR - https://arxiv.org/abs/2610.40338
AB - Electronic grand-canonical density functional theory captures how structure and electronic charge respond to electrode potential and, together with statistical mechanics, how these responses give rise to emergent phenomena. However, its computational cost limits the system sizes and sampling times accessible to first- principles simulations. Here, we introduce a differentiable architecture that represents the grand potential and obtains forces and electronic charge as its derivatives, exactly satisfying the mixed-derivative constraints required for thermodynamic consistency, and implement it within the equivariant MACE framework as GC- MACE. We demonstrate more accurate joint learning across multiple electrochemical interfaces and improved transferability to thicker water films relative to previous models, while enabling constant-potential simulations at substantially larger length and time scales than accessible to ab initio molecular dynamics. With broad training data, the framework offers a route to thermodynamically consistent foundation interatomic potentials for the electronic grand canonical ensemble
ER -