Numerical and Physics-Informed Neural Network Analysis for the Boussinesq-Type Equation
We consider in this article the numerical analysis of the Boussinesq equation. The numerical results are based on a finite element discretization in space and a finite difference scheme in time. Furthermore, we introduce a Physics-Informed Neural Network (PINN) and explore its use in solving the Boussinesq equation, comparing its performance with the traditional numerical approach.
Authors
- Abderrahmane Beniani (ORCID: https://orcid.org/0000-0002-5518-253X)
- Saleh Fahad Aljurbua (ORCID: https://orcid.org/0009-0004-1971-9418)
- Ahmed Bchatnia (ORCID: https://orcid.org/0000-0003-3795-5081)
- Boumediene Boukhari
Institutions
- Tunis University (TN)
- Qassim University (SA)
- Université de ain Témouchent (DZ)
- Tunis El Manar University (TN)
Publication Details
- Journal
- Journal of Nonlinear Mathematical Physics
- Published
- 2025-11-25
- DOI
- https://doi.org/10.1007/s44198-025-00353-x
- Primary Topic
- Model Reduction and Neural Networks
- Type
- article
- Field-Weighted Citation Impact
- 0.00