EUVIMEDEUVIMED entdecken
Crossref

A Flow-Rate-Conserving CNN-Based Domain Decomposition Method for Blood Flow Simulations

Simon Klaes, Axel Klawonn, Natalie Kubicki, Martin Lanser, Kengo Nakajima, Takashi Shimokawabe, Janine Weber-Hamacher

SIAM Journal on Scientific Computing · 31.12.2026 · 48 (6) · C1437-C1463

DOI: 10.1137/25m1802845 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 04.11.2026. Verfasst von Simon Klaes und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Helmholtz Association of German Research Centres, Information Technology Center, University of Tokyo, Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work aims to predict blood flow with non-Newtonian viscosity in stenosed arteries using convolutional neural network (CNN) surrogate models. An alternating Schwarz domain decomposition method is proposed which uses CNN-based subdomain solvers. A universal subdomain solver (USDS) is trained on a single, fixed geometry and then applied for each subdomain solve in the Schwarz method. Results for two-dimensional stenotic arteries of varying shape and length for different inflow conditions are presented and statistically evaluated. One key finding, when using a limited amount of training data, is that incorporating a physics-aware constraint, as, in our case, flow rate conservation, into the USDS improves the prediction accuracy and convergence behavior of the Schwarz method compared to a purely data-driven USDS. As the USDS is a data-driven, inexact subdomain solver, admissible parameter ranges for the geometry and inflow configurations must be defined and tested.

Förderung

  • Helmholtz Association of German Research Centres
  • Information Technology Center, University of Tokyo
  • Deutsche Forschungsgemeinschaft
  • Friedrich-Alexander-Universität Erlangen-Nürnberg
  • Federal and Bavarian state authorities
  • Helmholtz School for Data Science in Life, Earth, and Energy

Zitieren

APA

Klaes, S., Klawonn, A., Kubicki, N., Lanser, M., Nakajima, K., Shimokawabe, T., & Weber-Hamacher, J. (2026). A Flow-Rate-Conserving CNN-Based Domain Decomposition Method for Blood Flow Simulations. SIAM Journal on Scientific Computing, 48(6), C1437-C1463. https://doi.org/10.1137/25m1802845

Vancouver

Klaes S, Klawonn A, Kubicki N, Lanser M, Nakajima K, Shimokawabe T, et al. A Flow-Rate-Conserving CNN-Based Domain Decomposition Method for Blood Flow Simulations. SIAM Journal on Scientific Computing. 2026;48(6):C1437-C1463. doi:10.1137/25m1802845

BibTeX
@article{Klaes2026,
  author = {Klaes, Simon and Klawonn, Axel and Kubicki, Natalie and Lanser, Martin and Nakajima, Kengo and Shimokawabe, Takashi and Weber-Hamacher, Janine},
  title = {A Flow-Rate-Conserving CNN-Based Domain Decomposition Method for Blood Flow Simulations},
  journal = {SIAM Journal on Scientific Computing},
  year = {2026},
  volume = {48},
  number = {6},
  pages = {C1437--C1463},
  doi = {10.1137/25m1802845}
}
Kostenlos starten →