Michele Alessandro Bucci

Papers

Total Citations

H-Index

About

Michele Alessandro Bucci is a researcher at the forefront of data-driven modeling and machine learning for dynamical systems. His work bridges the gap between traditional computational physics and modern artificial intelligence, with a particular focus on developing algorithms that can learn complex physical behaviors from data. Bucci’s most notable contribution is his pioneering application of curriculum learning—a training strategy that gradually increases problem difficulty—to improve the efficiency and accuracy of neural network models for dynamical systems. His 2023 paper on this topic, which has already garnered 13 citations, demonstrates how structured training can overcome challenges in learning long-term temporal dependencies, a critical issue in fields like fluid dynamics and climate modeling. Beyond this, Bucci’s research explores reduced-order modeling and sparse identification of dynamics, offering tools that enable faster simulations without sacrificing fidelity. His work is highly cited for its practical impact, helping engineers and scientists build more robust predictive models from limited data. Bucci’s innovative approach positions him as a key figure in the growing intersection of machine learning and physical sciences, inspiring new methods for tackling nonlinear, high-dimensional problems.