MS191B Exploring New Avenues for the Interaction of Numerical Methods for PDEs and Deep Learning II
MS Corresponding Organizer: Mr. Paolo Zunino (MOX, Department of Mathematics, Politecnico di Milano)
Chaired by:
Prof. Kent-Andre Mardal (University of Oslo / Simula Research Laboratory , Norway) , Mr. Paolo Zunino (MOX, Department of Mathematics, Politecnico di Milano , Italy)
Prof. Kent-Andre Mardal (University of Oslo / Simula Research Laboratory , Norway) , Mr. Paolo Zunino (MOX, Department of Mathematics, Politecnico di Milano , Italy)
Scheduled presentations:
-
Neural Operator Surrogates for Elliptic PDEs
C. Marcati*, C. Schwab, J. Zech -
Neural latent dynamics models
S. Fresca*, N. Farenga, A. Manzoni -
A non-intrusive mesh-free surrogate model to address geometrical variability in patient-specific hemodynamics
R. Tenderini*, L. Pegolotti, A. Marsden, S. Deparis -
PoroTwin: Digital twins and machine learning for laboratory-scale porous media
E. Keilegavlen*, E. Fonn, K. Johanessen, K. Eikehaug, J. Both, M. Fernø, T. Kvamsdal, A. Rasheed, J. Nordbotten -
Physics Informed Neural Networks for a Peridynamic Inverse Problem
F. Difonzo*, L. Lopez, S. Pellegrino -
An Experimental Analysis of effects of different Training Methods for the Accuracy and the Computational Cost of PINNs
F. Colace, D. Conte, A. Lorusso, G. Pagano, B. Paternoster, C. Valentino*