I.N. Morozov

Where Foundation Machine-Learning Potentials Fail for Iron-Sulfide Defect Kinetics: Failure Modes, Pre-Flight Checks, and a DFT Benchmark of Vacancy-Anchored Hydrogen Migration in Pyrite, Marcasite, Mackinawite, and Greigite

This dataset and code package accompanies the study of foundation machine-learning interatomic potentials (MLIPs) for vacancy-anchored hydrogen migration in pyrite, marcasite, mackinawite and greigite. Foundation MLIPs offer inexpensive migration-barrier calculations, but their reliability for hydrogen defects in magne...