Electrochemical Interfaces at Constant Potential: Data-Efficient Transfer Learning for Machine-Learning-Based Molecular Dynamics

2025/11/24 by Bianchi, Michele Giovanni, Fiorentin, Michele Re, Risplendi, Francesca +4
Energy · Materials Science · #CO2 Reduction Techniques and Catalysts #Chemical Physics (physics.chem-ph) #Computational Physics (physics.comp-ph) #Electrocatalysts for Energy Conversion #FOS: Physical sciences #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci)

paper · doi:10.48550/arxiv.2511.19338

openalex publication_date 2025/11/24 · openalex created_date 2025/11/27 · openalex updated_date 2026/07/28

Abstract

Simulating electrified metal/water interfaces with explicit solvent under constant potential is essential for understanding electrochemical processes, yet remains prohibitively expensive with ab initio methods. We present TRECI, a data-efficient workflow for constructing machine learning force-fields (ML-FFs) that achieve ab initio-level accuracy in electronically grand-canonical molecular dynamics. By leveraging transfer learning from general-purpose and domain-specific models, TRECI enables stable and accurate simulations across a wide potential range using a reduced number of reference configurations. This efficiency allows the use of high-level meta-GGA functionals and rigorous surface-electrification schemes. Applied to Cu(111)/water, models trained on just one thousand configurations yield accurate molecular dynamics simulations, capturing bias-dependent solvent restructuring effects not previously reported. TRECI offers a general strategy for characterising diverse materials and interfacial chemistries, significantly lowering the cost of realistic constant-potential simulations and expanding access to quantitative electrochemical modelling.

Citations

• Machine Learning the Energetics of Electrified Solid/Liquid Interfaces
• Fast and Fourier Features for Transfer Learning of Interatomic Potentials
• A constant potential reactor framework for electrochemical reaction simulations
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• A foundation model for atomistic materials chemistry
• Converging Divergent Paths: Constant Charge vs. Constant Potential Energetics in Computational Electrochemistry
• Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales
• Accurate and numerically efficient r²SCAN meta-generalized gradient approximation
• Strongly Constrained and Appropriately Normed Semilocal Density Functional
• From ultrasoft pseudopotentials to the projector augmented-wave method
• Efficient iterative schemes forab initiototal-energy calculations using a plane-wave basis set
• Ab initiomolecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium

Related

• Machine learning accelerated finite-field simulations for electrochemical interfaces
• A constant potential reactor framework for electrochemical reaction simulations
• How Realistic are Idealized Copper Surfaces? A Machine Learning Study of Rough Copper-Water Interfaces
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• Machine Learning the Energetics of Electrified Solid/Liquid Interfaces