EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

PHYSICS-INFORMED NEURAL NETWORKS MODIFICATION FOR SOLVING 2D SHALLOW WATER EQUATIONS

NURSYIVA IRSALINDA, MAHARANI ABU BAKAR, NORIZAN MOHAMED

Journal of Mathematical Sciences and Informatics · 24.06.2026 · 6 (1)

DOI: 10.46754/jmsi.2026.06.003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mathematical Sciences and Informatics, online erschienen am 24.06.2026. Verfasst von NURSYIVA IRSALINDA und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the use of Physics-Informed Neural Networks (PINN) for solving the two-dimensional shallow water equations (SWE) on a flat bed and proposes a modified PINN with dynamic mesh-refinement strategy that adaptively increases the density of collocation points in critical or stiff regions such as propagating wave fronts and rapidly varying gradients. In the proposed framework, shallow-water physics is enforced as soft constraints in the loss, with initial and boundary conditions embedded to ensure a well-posed formulation without labelled targets. We evaluated fully connected architectures using the Adaptive Moment Estimation (Adam) and Limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) optimisation algorithms. Fully connected neural networks are trained using a combination of Adam and L-BFGS optimisers, and a FDM solution is employed as a reference for quantitative comparison. The standard PINN and its dynamically refined variant are evaluated against the FDM benchmark in terms of convergence behaviour and predictive accuracy. The results show that the refined PINN concentrates collocation points in stiff regions, reduces errors near wave fronts, and achieves accuracy closer to FDM with faster convergence.

Zitieren

APA

IRSALINDA, N., BAKAR, M. A., & MOHAMED, N. (2026). PHYSICS-INFORMED NEURAL NETWORKS MODIFICATION FOR SOLVING 2D SHALLOW WATER EQUATIONS. Journal of Mathematical Sciences and Informatics, 6(1). https://doi.org/10.46754/jmsi.2026.06.003

Vancouver

IRSALINDA N, BAKAR MA, MOHAMED N. PHYSICS-INFORMED NEURAL NETWORKS MODIFICATION FOR SOLVING 2D SHALLOW WATER EQUATIONS. Journal of Mathematical Sciences and Informatics. 2026;6(1). doi:10.46754/jmsi.2026.06.003

BibTeX
@article{IRSALINDA2026,
  author = {IRSALINDA, NURSYIVA and BAKAR, MAHARANI ABU and MOHAMED, NORIZAN},
  title = {PHYSICS-INFORMED NEURAL NETWORKS MODIFICATION FOR SOLVING 2D SHALLOW WATER EQUATIONS},
  journal = {Journal of Mathematical Sciences and Informatics},
  year = {2026},
  volume = {6},
  number = {1},
  doi = {10.46754/jmsi.2026.06.003}
}
Kostenlos starten →