GIMC SIMAI Young 2026

Session

MS07.2 - Recent Advances in Data-Driven Surrogate Modeling

5 Jun 2026, 11:15

Pisa

150. Hierarchical Model Reduction for Patient-Specific Vascular Flows

Erika Temellini (Politecnico di Milano)

05/06/2026, 11:15

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Hierarchical Model (HiMod) reduction is a mathematical technique developed to accurately model problems exhibiting an intrinsic dominant directionality (e.g., in pipe-like domains) at an affordable computational effort. HiMod reduction has been successfully employed in several applications, including hemodynamics [1] and acoustic wave propagation [2].

The approach relies on a...

129. DATA-DRIVEN REDUCED ORDER MODEL FOR LAMINAR FLUID-STRUCTURE PROBLEM

Mazhar Shehzad (IMT School Of Advance Studies Luccq)

05/06/2026, 11:30

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Fluid-Structure Interaction (FSI) plays a crucial role in predicting the dynamic response of systems across diverse engineering applications, from aeroelasticity to biomechanics. While high-fidelity Computational Fluid Dynamics (CFD) accurately captures the complex physics of these moving-boundary problems, the computational cost of resolving the deforming domains at every time step is very...

114. Reduced-Order Modeling of Steady Cylinder Flow via POD-Based Surrogate Models

Shahid Ali (MUSAM Research Unit,IMT School for Advanced Studies Lucca ,Italy)

05/06/2026, 11:45

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Many engineering and scientific applications involve the simulation of incompressible flows around bluff bodies. Among these problems, flow past a circular cylinder is one of the most widely studied benchmark cases for understanding wake behavior and testing numerical methods. Although the geometry is simple, accurately resolving the flow often requires solving the Navier–Stokes...

30. Efficient Bayesian Inverse UQ via Online Adaptive Gaussian Process Surrogates and Adaptive Delayed-Acceptance MCMC

Filippo Zacchei (Politecnico di Milano)

05/06/2026, 12:00

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Inverse uncertainty quantification (UQ) tasks, such as Bayesian parameter estimation, are computationally demanding when the forward model is a physics-based numerical solver. In particular, for PDE-governed systems, full-order discretizations (e.g., finite element or finite volume models) make conventional Markov chain Monte Carlo (MCMC) sampling prohibitively expensive due to the large...

49. Scientific Machine Learning for Forward and Inverse Problems in Cardiac Electrophysiology

Edoardo Centofanti (University of Pavia)

05/06/2026, 12:15

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Computational cardiology is based on the numerical solution of complex partial differential equations to model cardiac electrophysiology from non-invasive measurements. However, high-resolution simulations on anatomically realistic geometries are computationally expensive, whereas clinical practice demands rapid, interpretable, and application-oriented predictions. In this talk, we highlight...

121. Hybrid Physics–Data-Driven Reduced Order Surrogate for Turbulent Flows on Collocated Grids

Kabir Bakhshaei (Sant’Anna School of Advanced Studies and University of Pisa)

05/06/2026, 12:30

MS07 - Recent Advances in Data-Driven Surrogate Modeling

The construction of reliable surrogate models for turbulent flows remains a major challenge in scientific machine learning. While projection-based Reduced Order Models (ROMs) provide mathematically grounded low-dimensional representations of fluid systems, standard Galerkin approaches often fail to produce physically consistent reduced turbulence closures.
In this work, we propose a hybrid...

68. Fast and Accurate Reconstruction of 3D Cardiac Displacement Fields from Sparse MRI-like Data via PBDW

Francesco Mantegazza (University of Graz)

05/06/2026, 12:45

MS07 - Recent Advances in Data-Driven Surrogate Modeling

Personalized cardiac diagnostics require accurate reconstruction of myocardial displacement fields from limited clinical imaging data. In this work, we propose an enhanced Parametrized-Background Data-Weak [1] framework for the recovery of 3D cardiac displacement fields from sparse, MRI-like observations, designed for fast and robust online application. The main contribution is the...