Data driven approaches for complex physical systems
 Organizer(s):
Name:
Affiliation:
Country:
Li Wang
University of Minnesota
USA
Rongjie Lai
Purdue University
USA
 Introduction:  
  The growing availability of large-scale datasets is reshaping the landscape of physical modeling. While fundamental physical laws continue to underpin our understanding of physical systems, data offers new opportunities—enabling the replacement of empirical constitutive relations with learned models, or development of surrogate models for efficient inference. These advances highlight two key areas where deep learning has made significant strides: model prediction and operator learning. This special session aims to bring together leading researchers and practitioners to share insights and advance the frontiers of how deep learning can transform the classical field of applied and computational mathematics. By fostering collaboration and dialogue, we hope to accelerate progress in the development of data-driven approaches for modeling complex physical systems.