Physics informed neural networks for an inverse problem in peridynamic models

FV Difonzo, L Lopez, SF Pellegrino - Engineering with Computers, 2024 - Springer
Deep learning is a powerful tool for solving data driven differential problems and has come
out to have successful applications in solving direct and inverse problems described by …

[HTML][HTML] State Dependent Riccati for dynamic boundary control to optimize irrigation in Richards' equation framework

A Alla, M Berardi, L Saluzzi - Mathematics and Computers in Simulation, 2025 - Elsevier
We present an approach for the optimization of irrigation in a Richards' equation framework.
We introduce a proper cost functional, aimed at minimizing the amount of water provided by …

[PDF][PDF] Analysis of a nonlinear problem involving discrete and proportional delay with application to Houseflies model

K Shah, M Sher, M Sarwar, T Abdeljawad - AIMS Mathematics, 2024 - aimspress.com
This manuscript established a comprehensive analysis of a general class of fractional order
delay differential equations with Caputo-Fabrizio fractional derivative (CFFD). Functional …

Stabilized explicit peer methods with parallelism across the stages for stiff problems

G Pagano - Applied Numerical Mathematics, 2025 - Elsevier
In this manuscript, we propose a new family of stabilized explicit parallelizable peer methods
for the solution of stiff Initial Value Problems (IVPs). These methods are derived through the …

[HTML][HTML] Convergence analysis of a spectral numerical method for a peridynamic formulation of Richards' equation

FV Difonzo, SF Pellegrino - Mathematics and Computers in Simulation, 2024 - Elsevier
We study the implementation of a Chebyshev spectral method with forward Euler integrator
proposed in Berardi et al.(2023) to investigate a peridynamic nonlocal formulation of …

[HTML][HTML] Investigating neural networks with groundwater flow equation loss

VS Di Cola, V Bauduin, M Berardi, F Notarnicola… - … and Computers in …, 2025 - Elsevier
Abstract Physics-Informed Neural Networks (PINNs) are considered a powerful tool for
solving partial differential equations (PDEs), particularly for the groundwater flow (GF) …

[HTML][HTML] Impact of collocation point sampling techniques on PINN performance in groundwater flow predictions

V Bauduin, S Cuomo, VS Di Cola - Journal of Computational Mathematics …, 2025 - Elsevier
Abstract Physics-Informed Neural Networks (PINNs) represent a promising methodology for
addressing partial differential equations in scientific computing. This study examines …

A feedback control strategy for optimizing irrigation in a Richards' Equation framework

A Alla, M Berardi, L Saluzzi - arxiv preprint arxiv:2407.06477, 2024 - arxiv.org
We present an approach for the optimization of irrigation in a Richards' equation framework.
We introduce a proper cost functional, aimed at minimizing the amount of water provided by …