AI and the World's Hard Problems · Chemistry & materials · arXiv · 2026-10-19
Electrified Metal-Water Interfaces at Constant Potential: Data-Efficient Transfer Learning for Machine-Learning-Based Molecular Dynamics
Simulating electrified metal-water interfaces under constant potential with explicit solvent is prohibitively expensive with ab initio methods. TRECI uses transfer learning from general-purpose and domain-specific models to build machine-learning force fields from a reduced number of reference configurations. For Cu(111)-water, models trained on about one thousand configurations give accurate molecular dynamics and capture bias-dependent solvent restructuring.