Skip to main content
People

Stefania Fresca

Faculty Photo

Assistant Professor
Mechanical Engineering

Biography

Stefania Fresca is Assistant Professor in Physics-based Machine Learning at the Department of Mechanical Engineering at University of Washington, Seattle.


In 2017, she started her Ph.D. in the “Mathematical Models and Methods in Engineering” Program at MOX (Laboratory for Modeling and Scientific Computing) - Department of Mathematics at Politecnico di Milano, Italy, in the framework of the ERC Advanced Grant Project iHEART led by Prof. Alfio Quarteroni and devoted to cardiac modeling. After obtaining her Ph.D. Degree cum laude in 2021, she was recognized the Runner-up Best Ph.D. Award in Biomedical Engineering at the 7th International Conference on Computational & Mathematical Biomedical Engineering (CMBE22). Following her Ph.D., she spent two years as a Post-Doctoral Research Fellow at MOX and in 2023 started an Assistant Professorship in Numerical Analysis. From September 2024 to March 2025, she visited the Departments of Computer Science, and Applied Mathematics and Theoretical Physics at University of Cambridge, hosted by Prof. Pietro Liò and Prof. Carola Schönlieb.


Education

  • Ph.D. in Mathematical Models and Methods in Engineering, MOX (Laboratory for Modeling and Scientific Computing) - Department of Mathematics, Politecnico di Milano, Italy, 2021
  • M.S. in Mathematical Engineering - Computational Science and Engineering, Politecnico di Milano, Italy, 2017
  • B.S. in Mathematical Engineering, Politecnico di Milano, Italy, 2013

Previous appointments

  • Junior Assistant Professor in Numerical Analysis, MOX (Laboratory for Modeling and Scientific Computing) - Department of Mathematics, Politecnico di Milano, Italy, 2023
  • Post-doc Research Fellow, MOX (Laboratory for Modeling and Scientific Computing) - Department of Mathematics, Politecnico di Milano, Italy, 2020

Research Statement

Prof. Fresca's research interests and expertise include scientific machine learning, reduced order modeling (data dimensionality reduction), deep learning, digital twins, and numerical approximation of PDEs, with several applications to engineering problems. Her current focus is on operator learning in small data contexts, structure preserving and multi-scale deep learning for applications ranging from cardiac modeling (cardiac electrophysiology) to computational mechanics (fluid dynamics, flow control and turbulence modeling).


Select publications

  1. N. Farenga, S. Fresca, S. Brivio, A. Manzoni. On latent dynamics learning in nonlinear reduced order modeling. Neural Networks, 185, 107146, 2025. https://doi.org/10.1016/j.neunet.2025.107146
  2. S. Brivio, S. Fresca, A. Manzoni. PTPI-DL-ROMs: pre-trained physics-informed deep learning-based reduced order models for nonlinear parametrized PDEs. Computer Methods in Applied Mechanics and Engineering, 432, 117404, 2024. https://doi.org/10.1016/j.cma.2024.117404
  3. N. R. Franco, S. Fresca, A. Manzoni, P. Zunino. Approximation bounds for convolutional neural networks in operator learning. Neural Networks, 161, 129-141, 2023. https://doi.org/10.1016/j.neunet.2023.01.029
  4. S. Fresca, A. Manzoni. POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition. Computer Methods in Applied Mechanics and Engineering, 388, 114181, 2022. https://doi.org/10.1016/j.cma.2021.114181
  5. S. Fresca, A. Manzoni, L. Dede’. A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs. Journal of Scientific Computing, 87(2):1-36, 2021. https://doi.org/10.1007/s10915-021-01462-7