EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Structurally corrected invariant-preserving neural networks for conservative dynamical systems: a statistically validated approach

Fatima Ouaar

Scientific Journal of King Faisal University: Basic and Applied Sciences · 2026-06 · 27 (1)

DOI: 10.1007/s44523-026-00007-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Journal of King Faisal University: Basic and Applied Sciences, online erschienen am 26.05.2026. Verfasst von Fatima Ouaar. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper a structural correction in neural network architecture for the long-time integration of conservative dynamical systems is used to overcome uncontrolled invariant drift existing in standard physics-informed formulations. The Structurally Corrected IP-PINN is used to solve the Lotka–Volterra predator–prey system where the multiplicative architectural correction to the invariant manifold demonstrates from a statistical significance perspective improvements beyond both baseline and soft-constraint methods (Welch’s t-test, p

Zitieren

APA

Ouaar, F. (2026). Structurally corrected invariant-preserving neural networks for conservative dynamical systems: a statistically validated approach. Scientific Journal of King Faisal University: Basic and Applied Sciences, 27(1). https://doi.org/10.1007/s44523-026-00007-7

Vancouver

Ouaar F. Structurally corrected invariant-preserving neural networks for conservative dynamical systems: a statistically validated approach. Scientific Journal of King Faisal University: Basic and Applied Sciences. 2026;27(1). doi:10.1007/s44523-026-00007-7

BibTeX
@article{Ouaar2026,
  author = {Ouaar, Fatima},
  title = {Structurally corrected invariant-preserving neural networks for conservative dynamical systems: a statistically validated approach},
  journal = {Scientific Journal of King Faisal University: Basic and Applied Sciences},
  year = {2026},
  volume = {27},
  number = {1},
  doi = {10.1007/s44523-026-00007-7}
}
Kostenlos starten →