Cesare Franchini

Full Professor @ Uni Bologna

Full Professor @ Uni Vienna

First Principles and ML-AI Quantum Materials

Theoretical understanding and computational modeling of quantum materials  using quantum mechanical first principles methodologies and AI algorithm. Quantum Materials: Mott physics, polaron physics, non-collinear magnetism, excitons, surface scince. Machine Learning techniques: ML interatomic potentials, (deep) Neural Networks, Computer Vision, Normalizing Flow, Bayesian optimization.

Machine Learning and Many-body Materials Physics:

Machine Learning Small Polaron Dynamics

Magnetite (001)/water interface from NN potentials

N-doped LuH3 superconductor, Nature Comm. (2024)

Feynman's diagrams through normalizing flow, PRR (2024)

ML for large scale surface pattern, npj Comp. Mat 2024

Quantum paraelectricity  in SrTiO3, PRM 2023

KTaO3 by Machine‐Learned Force Fields, Adv Quan Techn (2023) 

Automated microscopy images, ML Sci & Tech (2023)

Diffusion of vacancies by NN potentials, JPC (2023)

Deep learning theFRG, PRL (2022)

ML for polaron configurational space, npj Comp. Mat 2022