MELTS: Fully Automated Active Learning for Fewest-Switches Surface Hopping Dynamics
Matheus de Oliveira Bispo, Rafael S. Mattos, Max Pinheiro, Bidhan Chandra Garain, Pavlo O. Dral, Mario Barbatti
Abstract
Photochemical processes span time scales from femtoseconds to nanoseconds, and their simulation via fewest-switches surface hopping (FSSH) requires a large number of computationally expensive electronic structure evaluations. Machine learning (ML) interatomic potentials can reduce this cost; however, they must be trained on data sets that capture the most relevant regions of configurational space. We present MELTS, a fully automated active learning (AL) program for FSSH that iteratively improves ML models by using trajectory propagation to guide sampling. MELTS integrates Newton-X and MLatom through socket-based communication, minimizing I/O overhead and enabling large-scale simulations with a user-friendly interface. We validate the AL protocol implemented in MELTS on two contrasting systems: ultrafast fulvene dynamics (tens of femtoseconds) and nanosecond-scale pyrene fluorescence. In both cases, MELTS delivers quantitative agreement with reference quantum results while reducing computational time by up to 3 orders of magnitude. This demonstrates that MELTS can efficiently generate accurate ML potentials for photochemical processes across a wide range of time scales.