GIMC SIMAI Young 2026

Session

MS03 - Graph Neural Networks for Computational Physics

4 Jun 2026, 11:15

Pisa

25. Learning Vascular Hemodynamics: Physics-Informed GNNs Inference from Capillary Networks to Pulsatile Flow

Paolo Botta (MOX, Department of Mathematics, Politecnico di Milano)

04/06/2026, 11:15

MS03 - Graph Neural Networks for Computational Physics

Simulating microvascular blood flow in anatomically realistic networks remains a formidable computational task. The intrinsic multiscale structure of the vascular system, the geometric heterogeneity of capillary beds, and the nonlinear rheological behavior of blood in the microcirculation jointly lead to highly complex mathematical models whose direct numerical solution is often prohibitively...

28. Graph-Based Nonlinear Reduced-Order Modeling for Time-Domain Electromagnetics

Carlotta Filippin (Université Côte d'Azur, Inria, CNRS, LJAD)

04/06/2026, 11:30

MS03 - Graph Neural Networks for Computational Physics

Numerical modelling plays a crucial role in revealing the behaviour of light and matter interactions at the nanoscale, exploiting computational schemes such as the Discontinuous Galerkin Time-Domain (DGTD) method. Given the computational complexity associated to this task, we study reduced-order modelling (ROM) due to the pressing need for fast surrogate models capable of handling physically...

35. Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs

Lorenzo Tomada (SISSA)

04/06/2026, 11:45

MS03 - Graph Neural Networks for Computational Physics

Graph Neural Networks (GNNs) are emerging as powerful tools for nonlinear Model Order Reduction (MOR) of time-dependent parameterized Partial Differential Equations (PDEs) [1].
However, existing methodologies struggle to combine geometric inductive biases with interpretable latent behavior, overlooking dynamics-driven features or disregarding geometric information.
In this work, we address...

127. Coupling Phisically Informed Graph Neural Networks with External Solvers

Niccolò Picchiarelli (Sant'Anna School of Advanced Studies)

04/06/2026, 12:00

MS03 - Graph Neural Networks for Computational Physics

Machine Learning (ML) methods for solving Partial Differential Equations (PDEs) have recently undergone unprecedented development. Physics-Informed Neural Networks (PINNs) have gained significant attention for their ability to integrate underlying physics into learning frameworks. However, classic PINNs rely on Automatic Differentiation (AD) to compute physics-based loss terms. During...

141. Physics Informed Graph Neural Networks for Nonlinear Dynamics

Gennaro Calandriello (Scuola Superiore Sant'Anna)

04/06/2026, 12:15

MS03 - Graph Neural Networks for Computational Physics

Deep learning architectures have recently been investigated for fast prediction in parametric PDEs. Within the Model Order Reduction (MOR) paradigm, an offline stage projects the nonlinear solution space into a low-dimensional manifold, and the compressed latent representation enables rapid, accurate predictions with a small computational cost.
In particular, Graph Neural Networks have shown...

165. Physics-constrained identification of graph-based thermal networks for spacecraft digital twins

Luca Sosta (Politecnico di Milano)

04/06/2026, 12:30

MS03 - Graph Neural Networks for Computational Physics

Reconstructing a thermal model capable of efficiently simulating the behavior of a spacecraft from sparse and localized temperature measurements remains a challenging task. To solve this challenge,
we introduce a physically-constrained calibration framework for Lumped Parameter Thermal Models (LPTMs), formulated as a trajectory-based inverse problem for graph dynamical systems. The model...