EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Numerically-Inspired Novel Loss Functions for Physics-Informed Neural Networks of Hyperbolic Conservation Laws

Vikas Kumar Jayswal, Sandeep Kumar Paul

Boletim da Sociedade Paranaense de Matemática · 29.10.2026 · 44 (14) · 1-13

DOI: 10.5269/bspm.85868 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Boletim da Sociedade Paranaense de Matemática, online erschienen am 29.10.2026. Verfasst von Vikas Kumar Jayswal und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics-Informed Neural Networks (PINNs) present a compelling mesh-free, data-light alternativefor solving partial differential equations, however, they encounter significant difficulties whenapplied to hyperbolic conservation laws that develop shocks and discontinuities. Classicalnumerical techniques specifically, Essentially Non-Oscillatory (ENO) schemes, Total VariationDiminishing (TVD) limiters, and entropy-stability conditions have long been employed to addressthese challenges. In this work, we introduce five differentiable loss-function components thattranslate these established numerical ideas directly into the PINN optimization objective:(i) Arc-Length Regularization, drawn from ENO smoothness indicators,(ii) TVD Loss, which penalizes spurious oscillations,(iii) Conservation Loss, which enforces global integral invariants,(iv) Shock-Aware Smoothness, which adaptively weights second-derivative penalties in thevicinity of discontinuities, and(v) Entropy-Stable Loss, which imposes physical admissibility through the entropy inequality.Six PINN variants are evaluated against three canonical benchmarks: linear advection with asmooth initial profile, and the Burgers equation with shock formation. The proposed lossfunctions consistently reduce final PDE residuals and improve solution accuracy, at the costof only a 20–40\% increase in computational overhead. This framework draws a principledconnection between classical numerical analysis and modern deep learning, offering a robustpath toward reliable PINNs for hyperbolic problems.

Zitieren

APA

Jayswal, V. K., & Paul, S. K. (2026). Numerically-Inspired Novel Loss Functions for Physics-Informed Neural Networks of Hyperbolic Conservation Laws. Boletim da Sociedade Paranaense de Matemática, 44(14), 1-13. https://doi.org/10.5269/bspm.85868

Vancouver

Jayswal VK, Paul SK. Numerically-Inspired Novel Loss Functions for Physics-Informed Neural Networks of Hyperbolic Conservation Laws. Boletim da Sociedade Paranaense de Matemática. 2026;44(14):1-13. doi:10.5269/bspm.85868

BibTeX
@article{Jayswal2026,
  author = {Jayswal, Vikas Kumar and Paul, Sandeep Kumar},
  title = {Numerically-Inspired Novel Loss Functions for Physics-Informed Neural Networks of Hyperbolic Conservation Laws},
  journal = {Boletim da Sociedade Paranaense de Matemática},
  year = {2026},
  volume = {44},
  number = {14},
  pages = {1--13},
  doi = {10.5269/bspm.85868}
}
Kostenlos starten →