By combining first-principles quantum simulations with a custom machine learning framework—Leopold (Learning of polaron dynamics)—the team has captured how polarons form and move through materials over nanosecond timescales. This work, co-authored with the University of Bologna, unlocks new insights into materials for solar energy, batteries, and next-gen electronics.
“Machine learning isn’t just speeding things up—it’s reshaping how we study quantum systems,” says co-first author Luca Leoni.
Read more:
Birschitzky, V.C., Leoni, L., Reticcioli, M., Franchini, C. Machine Learning Small Polaron Dynamics, Phys. Rev. Lett. 134, 216301 (2025).
DOI: 10.1103/PhysRevLett.134.216301
New Publication in Physical Review Letters
02.06.2025
