Predicting interface structure using the minima hopping method with a machine learning interatomic potential

Predicting atomic-scale interfacial structures remains a central challenge in materials science due to their structural complexity and the difficulty of direct comparison between computational and experimental results. In this study, we present an effective approach for interface structure prediction that integrates the minima hopping method (MHM) with the state-of-the-art machine-learning interatomic potential (MLIP), Allegro. We demonstrate that the MHM–Allegro approach provides a robust framework for predicting interfacial structures in the representative benchmark system, SrTiO 3 Σ 3(112)[110] tilt grain boundaries (GBs), consistently identifying the lowest-energy configurations across different stoichiometries. Furthermore, we introduce a novel strategy for constructing defect-representative training datasets without explicitly including defective configurations, and show that the resulting MLIP enables reliable interface structure prediction. The predictive capability of the approach is further validated through direct comparison with experimental observations of the SrTiO 3 Σ 5(310)[001] GB, where the predicted atomic configurations show strong agreement with experimental measurements. This work represents a significant step toward bridging the gap between ab initio predictions and experimentally observed interfacial structures.