Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
Abstract
Small polarons, formed when excess electrons become localized through lattice distortions, play a critical role in charge transport, catalysis, and degradation processes in transition-metal (TM) oxides. Whether universal machine-learning interatomic potentials (uMLIPs), which lack explicit electronic degrees of freedom, can describe them remains unclear. Here, we investigate H-induced electron localization across a range of TM oxides using a geometric descriptor based on TM-O bond-length expansion (Z-score) to identify polaronic distortions. We find that uMLIPs exhibit varying degrees of electron localization, from delocalized states to metastable small polarons, with their behavior strongly dependent on the training data and treatment of electronic correlations. In particular, the absence of Hubbard U corrections for specific TM cations in the training data leads to electron delocalization, in contrast to DFT+U predictions. Although some uMLIPs reproduce polaron hopping barriers during coupled proton-polaron transfer, all of them fail to stabilize spatially separated polaron-donor configurations, instead favoring localization near the H dopant.
Related
- Correcting the Liquid Densities of Universal Machine-Learning Interatomic Potentials Using Local-Number-Density Repulsion
- Applicability Domain of Universal Machine Learning Interatomic Potentials at Solid-State Battery Interfaces
- Reference Conventions and Structure Types, Rather Than 4f Occupancy, Shape Lanthanide Errors in Universal Machine-Learning Interatomic Potentials
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials
BibTeX
@misc{korostelev2026universal,
title = {{Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides}},
author = {Vladislav Korostelev and Pjotrs Žguns and Konstantin Klyukin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17352},
eprint = {2610.17352},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17352},
}
RIS
TY - UNPB
TI - Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
AU - Vladislav Korostelev
AU - Pjotrs Žguns
AU - Konstantin Klyukin
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17352
UR - https://arxiv.org/abs/2610.17352
AB - Small polarons, formed when excess electrons become localized through lattice distortions, play a critical role in charge transport, catalysis, and degradation processes in transition-metal (TM) oxides. Whether universal machine-learning interatomic potentials (uMLIPs), which lack explicit electronic degrees of freedom, can describe them remains unclear. Here, we investigate H-induced electron localization across a range of TM oxides using a geometric descriptor based on TM-O bond-length expansion (Z-score) to identify polaronic distortions. We find that uMLIPs exhibit varying degrees of electron localization, from delocalized states to metastable small polarons, with their behavior strongly dependent on the training data and treatment of electronic correlations. In particular, the absence of Hubbard U corrections for specific TM cations in the training data leads to electron delocalization, in contrast to DFT+U predictions. Although some uMLIPs reproduce polaron hopping barriers during coupled proton-polaron transfer, all of them fail to stabilize spatially separated polaron-donor configurations, instead favoring localization near the H dopant.
ER -