Physics Informed Neural Networks in Padova (PINN-PAD)

PADOVA, 22-23 February 2024
PROGRAM

Thursday, February 22 – Aula Nievo – Palazzo Bo
   
08.55 09.00
Opening Remarks
   
09.00 10.00

Anna Schwarz

Recent advances and failures in the machine-learning enhanced solution of PDEs

   
10.00 10.50

CT1  Y. Saleh

Spectral learning for solving molecular Schr÷dinger equations

   

CT2  M. Tanveer

Neural Network Approach to Learn Delay Differential Equations via Pseudospectral Collocation

10.50 11.20
Coffee Break at caffŔ Pedrocchi
   
11.20 12.20

Francesco Dalla Santa

Graph-informed neural network and discontinuity learning

   
12.20 13.10

CT3  E. Chinellato

Physics-Aware Deep Nonnegative Matrix Factorization

   

CT4  R. Boiger

Solving the Bateman Equation using Physics Informed Neural Networks

   
13.10 15.00
Lunch (not provided)
   
15.00 16.00

Gianluigi Rozza

Accelerating Numerical Simulations by Model Reduction with Scientific and Physics-Informed Machine Learning

   
16.00 16.50

CT5  G. A. D’Inverno

Physics Informed Graph Neural Networks for AC Optimal Power Flow

   

CT6 A. Jnini

Gauss-Newton Natural Gradient for Physics-Informed Computational Fluid Dynamics

   
16.50 17.20
Coffee Break at caffŔ Pedrocchi
   
17.20 18.20

Salvatore Cuomo

Computational Paradigms in Scientific Machine Learning

   
20.30
Social dinner at Restaurant:
Isola di Caprera, via Marsilio da Padova, 11



Friday, February 23 – Aula E Giurisprudenza – Palazzo Bo
   
09.00 10.00

Federica Bragone

Physics-Informed Neural Networks for Power Systems Applications

   
10.00 11.15

CT7  F. Difonzo

Physics Informed Neural Networks for an Inverse Problem in Peridynamic Models

   

CT8  A. Forootani

Application of Physics-Informed Neural Networks in Nonlinear Systems Identification and Parameter Estimation

   

CT9  M. Hoefler

Parameter estimation in cardiac biomechanical models based on physics-informed neural networks

   
11.15 11.45
Coffee Break at caffŔ Pedrocchi
   
11.45 13.00

CT10  A. Lovison

Brain memory working. Optimal control behavior for improved Hopfield-like models

   

CT11  F. J. Barraza Henriquez

Wavenumber-Robust Deep ReLU Neural Network Emulation in Acoustic Wave Scattering

   

CT12  F. Marchetti

Predicting coronal mass ejections’ travel times by using physics-informed loss functions

   
13.00 14.45
Lunch (not provided)
   
14.45 15.45

Paola Antonietti

Machine Learning-enhanced Polytopal Finite Element Methods

   
15.45 16.10

CT13  I. Bioli

Multi-Fidelity Neural Network Surrogate Modeling for Large-Scale Bayesian Inverse Problems

   
16.10 16.15
Concluding Remarks