Modeling the inner electric double layer using short-range machine learning potentials: A critical assessment
The Journal of Chemical Physics · 14.11.2026 · 165 (18)
DOI: 10.1063/5.0359674 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 11.11.2026. Verfasst von Lucas B T de Kam und 4 weiteren Autor:innen. Beteiligte Einrichtung: Leiden Institute of Chemistry, Leiden University, 2300RA Leiden, The Netherlands. Die Arbeit nennt 76 Literaturangaben. Gefördert von: Dutch Research Council, Nanyang Technological University.
Abstract (Originalsprache)
Atomistic simulations of electrochemical interfaces typically require large system sizes and long simulation times to obtain reliable thermodynamic properties. In this context, machine learning interatomic potentials (MLIPs) allow for computationally efficient sampling compared to density functional theory-based molecular dynamics simulations. Although conventional short-range MLIPs are recognized as inadequate for modeling the (potentially nanometer-wide) diffuse layer, they may still be capable of describing the inner electric double layer that is relevant for electrochemical reactions. Here, we evaluate the performance of common (short-ranged) MLIP architectures [the deep potential DP, the (graph) atomic cluster expansion-based models GRACE and MACE, and the pre-trained eSEN-OC25] for charged Au/electrolyte interfaces. In the evaluation, we focus on the effect of message passing and on the potentially adverse effect of data interference when training for a broad range of surface charges. Our results suggest that both local and message-passing models are able to reliably learn the interfacial structure when training on a single charge state. However, when trained on datasets that span multiple charge states, the MLIPs tested yield inconsistent predictions of interfacial water orientation and ion distributions. This behavior can be traced to the MLIPs being “blind” to the actual surface charge. Message-passing models show somewhat greater robustness to mixed-charge training data, likely due to their larger receptive field, but are still prone to artifacts and errors in the description of the interfacial structure. Overall, our results provide practical guidance on the expected accuracy and cross-charge-state transferability of short-ranged MLIPs for the description of the inner layer of electrode/electrolyte interfaces that will be relevant to their use in computational electrocatalysis.
Autor:innen und Institutionen
- Leiden Institute of Chemistry, Leiden University, 2300RA Leiden, The Netherlands.
- Department of Chemistry, TUM School of Natural Sciences, Technische Universität München, Lichtenbergstr. 4, 85748 Garching, Germany.
- State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, China.
- Theory and Computation of Energy Materials (IET-3), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany.
- Department of Chemical Engineering, University of Michigan, Ann Arbor, Michigan 48109, USA.
- School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore 637371, Singapore.
ORCID-Profile: Lucas B T de Kam, Jia-Xin Zhu, Ankit Mathanker, Katharina Doblhoff-Dier, Nitish Govindarajan
Förderung
- Dutch Research Council
- Nanyang Technological University
Zitieren
APA
de Kam, L. B. T., Zhu, J. X., Mathanker, A., Doblhoff-Dier, K., & Govindarajan, N. (2026). Modeling the inner electric double layer using short-range machine learning potentials: A critical assessment. The Journal of Chemical Physics, 165(18). https://doi.org/10.1063/5.0359674
Vancouver
de Kam LBT, Zhu JX, Mathanker A, Doblhoff-Dier K, Govindarajan N. Modeling the inner electric double layer using short-range machine learning potentials: A critical assessment. The Journal of Chemical Physics. 2026;165(18). doi:10.1063/5.0359674
BibTeX
@article{deKam2026,
author = {de Kam, Lucas B T and Zhu, Jia-Xin and Mathanker, Ankit and Doblhoff-Dier, Katharina and Govindarajan, Nitish},
title = {Modeling the inner electric double layer using short-range machine learning potentials: A critical assessment},
journal = {The Journal of Chemical Physics},
year = {2026},
volume = {165},
number = {18},
doi = {10.1063/5.0359674}
}
EUVIMED