EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural network-assisted refinement of traditional schemes for one-dimensional scalar conservation laws

Imre Fekete, Ferenc Izsák, Vendel P. Kupás

Advances in Computational Mathematics · 2026-10 · 52 (5)

DOI: 10.1007/s10444-026-10357-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Computational Mathematics, online erschienen am 17.09.2026. Verfasst von Imre Fekete und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nemzeti Kutatási Fejlesztési és Innovációs Hivatal.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A clear link is established between conventional numerical methods and neural network approximations for solving one-dimensional scalar conservation laws. The focus is on the construction of an appropriate flux term in the case of convex flux functions for improving the classical schemes. The first neural network developed here is able to rediscover Godunov’s method, while the second one emulates the behavior of a second-order slope-limiter function. In this way, by merging them, second-order reconstruction-based schemes can be developed. The networks presented here employ a minimal number of parameters, significantly reducing the complexity compared to previous approaches. These networks can also be linked consecutively to get a deep one corresponding to multiple time steps. Training them with an appropriate loss leads to stable schemes, improving even the classical methods without increasing their complexity.

Förderung

  • Nemzeti Kutatási Fejlesztési és Innovációs Hivatal

Zitieren

APA

Fekete, I., Izsák, F., & Kupás, V. P. (2026). Neural network-assisted refinement of traditional schemes for one-dimensional scalar conservation laws. Advances in Computational Mathematics, 52(5). https://doi.org/10.1007/s10444-026-10357-w

Vancouver

Fekete I, Izsák F, Kupás VP. Neural network-assisted refinement of traditional schemes for one-dimensional scalar conservation laws. Advances in Computational Mathematics. 2026;52(5). doi:10.1007/s10444-026-10357-w

BibTeX
@article{Fekete2026,
  author = {Fekete, Imre and Izsák, Ferenc and Kupás, Vendel P.},
  title = {Neural network-assisted refinement of traditional schemes for one-dimensional scalar conservation laws},
  journal = {Advances in Computational Mathematics},
  year = {2026},
  volume = {52},
  number = {5},
  doi = {10.1007/s10444-026-10357-w}
}
Kostenlos starten →