SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials
Abstract
Machine-learned interatomic potentials (MLIPs) enable simulations of larger atomistic systems over longer timescales than traditional ab initio methods but require large, diverse training data. Existing datasets lack comprehensive sampling of solid-liquid interfaces, which exhibit complex phenomena such as solvent layering and surface reconstruction critical for energy and catalytic materials. Here, we present SoLiD26, a curated solid-liquid interface dataset of 15.4 million first-principles structures with up to 576 atoms and 15 chemical elements for training and evaluating MLIPs. The structures were compiled from density functional theory (DFT) calculations, with most configurations originating from ab initio molecular dynamics (AIMD) simulations. SoLiD26 includes aqueous coinage metal interfaces, electrode-electrolyte systems, and selected bulk reference structures, calculated with VASP using the PBE functional and D3 dispersion corrections. The application of SoLiD26 for training and evaluating MLIPs is demonstrated with a suite of MACE models on a simple training, validation and test split. This dataset provides a valuable resource for advancing MLIP development targeted at modelling solid-liquid interfaces in electrochemical and catalytic systems.
Related
- Entropy-Guided Dataset Reduction for Machine-Learned Interatomic Potentials
- Correcting the Liquid Densities of Universal Machine-Learning Interatomic Potentials Using Local-Number-Density Repulsion
- Foundation interatomic potentials learn the practical chemistry they were never taught
- pdb2reaction: End-to-End Reaction-Path Elucidation from PDB Structures Using Machine-Learning Interatomic Potentials
- Applicability Domain of Universal Machine Learning Interatomic Potentials at Solid-State Battery Interfaces
BibTeX
@misc{busk2026solid26,
title = {{SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials}},
author = {Jonas Busk and Emil J. P. Frost and Yogeshwaran Krishnan and Henrik H. Kristoffersen and August E. G. Mikkelsen and Xueping Qin and Xin Yang and Heine A. Hansen and Arghya Bhowmik and Tejs Vegge},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.28013},
eprint = {2609.28013},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28013},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials
AU - Jonas Busk
AU - Emil J. P. Frost
AU - Yogeshwaran Krishnan
AU - Henrik H. Kristoffersen
AU - August E. G. Mikkelsen
AU - Xueping Qin
AU - Xin Yang
AU - Heine A. Hansen
AU - Arghya Bhowmik
AU - Tejs Vegge
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2609.28013
UR - https://arxiv.org/abs/2609.28013
AB - Machine-learned interatomic potentials (MLIPs) enable simulations of larger atomistic systems over longer timescales than traditional ab initio methods but require large, diverse training data. Existing datasets lack comprehensive sampling of solid-liquid interfaces, which exhibit complex phenomena such as solvent layering and surface reconstruction critical for energy and catalytic materials. Here, we present SoLiD26, a curated solid-liquid interface dataset of 15.4 million first-principles structures with up to 576 atoms and 15 chemical elements for training and evaluating MLIPs. The structures were compiled from density functional theory (DFT) calculations, with most configurations originating from ab initio molecular dynamics (AIMD) simulations. SoLiD26 includes aqueous coinage metal interfaces, electrode-electrolyte systems, and selected bulk reference structures, calculated with VASP using the PBE functional and D3 dispersion corrections. The application of SoLiD26 for training and evaluating MLIPs is demonstrated with a suite of MACE models on a simple training, validation and test split. This dataset provides a valuable resource for advancing MLIP development targeted at modelling solid-liquid interfaces in electrochemical and catalytic systems.
ER -