Data-driven Riemann solvers: A neural network approach and a hybrid solver
Physics of Fluids · 01.09.2025 · 37 (9)
DOI: 10.1063/5.0288995 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 19.09.2025. Verfasst von Xesús Nogueira und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Ministerio de Ciencia e Innovación, Axencia Galega de Innovación, Ministerio de Ciencia, Innovación y Universidades.
Abstract (Originalsprache)
The accurate and efficient numerical solution of the Riemann problem is the basis of Godunov-type schemes. Approximate Riemann solvers are widely used for their efficiency, although they exhibit inaccuracies and instabilities in challenging regimes such as strong rarefactions or near-vacuum conditions. This work explores the use of deep neural networks (NNs) to address these limitations. We present two distinct data-driven frameworks: first, a NN-based solver trained to predict the exact solution of the Riemann problem, and second, a high-performance hybrid scheme. The hybrid approach uses the standard Harten–Lax–van Leer-contact (HLLC) Riemann solver as the main solver, enhanced with a computationally inexpensive, physics-based detector that identifies interfaces where the HLLC solution is likely to be inaccurate or to fail. At these interfaces, the scheme selectively uses the pretrained NN to ensure a more accurate solution. Through a series of benchmark tests, we show that the NN solver accurately reproduces the exact solution of the Riemann problem, but at a significant computational cost. In contrast, the proposed hybrid solver achieves a comparable level of accuracy to the NN solver, while it requires nearly the same computational cost as the standard HLLC solver.
Förderung
- Ministerio de Ciencia e Innovación
- Axencia Galega de Innovación
- Ministerio de Ciencia, Innovación y Universidades
Zitieren
APA
Nogueira, X., Ramos, L., Seijo, S., Couceiro, I., Khelladi, S., & Ramírez, L. (2025). Data-driven Riemann solvers: A neural network approach and a hybrid solver. Physics of Fluids, 37(9). https://doi.org/10.1063/5.0288995
Vancouver
Nogueira X, Ramos L, Seijo S, Couceiro I, Khelladi S, Ramírez L. Data-driven Riemann solvers: A neural network approach and a hybrid solver. Physics of Fluids. 2025;37(9). doi:10.1063/5.0288995
BibTeX
@article{Nogueira2025,
author = {Nogueira, Xesús and Ramos, Lucía and Seijo, Sonia and Couceiro, Iván and Khelladi, Sofiane and Ramírez, Luis},
title = {Data-driven Riemann solvers: A neural network approach and a hybrid solver},
journal = {Physics of Fluids},
year = {2025},
volume = {37},
number = {9},
doi = {10.1063/5.0288995}
}
EUVIMED