Multi-fidelity Machine Learning Interatomic Potentials for Charged Point Defects
Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.