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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bianchi, Michele Giovanni, Fiorentin, Michele Re, Risplendi, Francesca, Pirri, Candido Fabrizio, Parrinello, Michele, Bonati, Luigi, Cicero, Giancarlo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911283925745664
author Bianchi, Michele Giovanni
Fiorentin, Michele Re
Risplendi, Francesca
Pirri, Candido Fabrizio
Parrinello, Michele
Bonati, Luigi
Cicero, Giancarlo
author_facet Bianchi, Michele Giovanni
Fiorentin, Michele Re
Risplendi, Francesca
Pirri, Candido Fabrizio
Parrinello, Michele
Bonati, Luigi
Cicero, Giancarlo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19338
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Electrochemical Interfaces at Constant Potential: Data-Efficient Transfer Learning for Machine-Learning-Based Molecular Dynamics
Bianchi, Michele Giovanni
Fiorentin, Michele Re
Risplendi, Francesca
Pirri, Candido Fabrizio
Parrinello, Michele
Bonati, Luigi
Cicero, Giancarlo
Computational Physics
Materials Science
Chemical Physics
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.
title Electrochemical Interfaces at Constant Potential: Data-Efficient Transfer Learning for Machine-Learning-Based Molecular Dynamics
topic Computational Physics
Materials Science
Chemical Physics
url https://arxiv.org/abs/2511.19338