Capturing the diffusive behavior of the multiscale linear transport equations by Asymptotic-Preserving Convolutional DeepONets

K Wu, XB Yan, S Jin, Z Ma - Computer Methods in Applied Mechanics and …, 2024 - Elsevier
In this paper, we introduce two types of novel Asymptotic-Preserving Convolutional Deep
Operator Networks (APCONs) designed to solve the multiscale time-dependent linear …

Asymptotic-preserving neural networks for multiscale kinetic equations

S Jin, Z Ma, K Wu - arXiv preprint arXiv:2306.15381, 2023 - arxiv.org
In this paper, we present two novel Asymptotic-Preserving Neural Networks (APNNs) for
tackling multiscale time-dependent kinetic problems, encompassing the linear transport …

New trends on the systems approach to modeling SARS-CoV-2 pandemics in a globally connected planet

G Bertaglia, A Bondesan, D Burini, R Eftimie… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper presents a critical analysis of the literature and perspective research ideas for
modeling the epidemics caused by the SARS-CoV-2 virus. It goes beyond deterministic …

Asymptotic-Preserving Convolutional DeepONets Capture the Diffusive Behavior of the Multiscale Linear Transport Equations

K Wu, X Yan, S Jin, Z Ma - arXiv preprint arXiv:2306.15891, 2023 - arxiv.org
In this paper, we introduce two types of novel Asymptotic-Preserving Convolutional Deep
Operator Networks (APCONs) designed to address the multiscale time-dependent linear …

Modelling contagious viral dynamics: a kinetic approach based on mutual utility

G Bertaglia, L Pareschi, G Toscani - arXiv preprint arXiv:2401.00480, 2023 - arxiv.org
The time evolution of a contagious viral disease is modeled as the dynamic progression of
different classes of populations that interact pairwise, aiming to improve their condition with …

A PINN approach for the online identification and control of unknown PDEs

A Alla, G Bertaglia, E Calzola - arXiv preprint arXiv:2408.03456, 2024 - arxiv.org
Physics-Informed Neural Networks (PINNs) have revolutionized solving differential
equations by integrating physical laws into neural network training. This paper explores …

Solving inverse and forward problems of multiscale epidemic spread with neural networks

G Bertaglia - PROCEEDINGS OF SIMAI 2023-THE XVI BIANNUAL …, 2023 - unibas.it
To account for spatial heterogeneity, the spatial spread of an infectious disease can be
described by a class of multiscale systems of partial differential equations, in which a portion …