Machine learning is rapidly transforming molecular dynamics simulations by enabling the construction of highly accurate interatomic potentials derived from high‐level quantum calculations. This ...
Researchers used machine learning interatomic potential (MLIP) calculations to narrow down the search for candidate dopants for a new type of photocatalytic tin oxide. MLIP calculations successfully ...
illustrating the comprehensive zero-shot benchmark of 19 universal machine learning interatomic potentials and the dominant impact of training data composition for surface energy prediction. A ...