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

Anchored Physics-Informed Neural Network for Two-Phase Flow Simulation in Heterogeneous Porous Media

Jingqi Lin, Xia Yan, Kai Zhang, Zhao Zhang, Jun Yao

InterPore Journal · 25.08.2025 · 2 (3) · IPJ250825-5

DOI: 10.69631/ipj.v2i3nr67 ↗

Kurz gefasst

Fachartikel in der Zeitschrift InterPore Journal, online erschienen am 25.08.2025. Verfasst von Jingqi Lin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, we propose a tensorization-anchoring strategy based on adaptive architectures to accelerate the computation of Enriched Physics-Informed Neural Networks (EPINN) for two-phase flow simulations. Specifically, we design an adaptive tensorization mechanism for the adjacency matrix embedding, the activation function, and the skip-gated connection in EPINN, which collectively expand the neural network's (NN) parameter space for learning more generalized patterns. Moreover, we developed an anchoring strategy by establishing Anchors-EPINN (An-EPINN). By detaching tensorization parameters from the computational graph and anchoring weighted nodes to fixed positions, the NN can benefit from tensorized fusion effects while reducing high-dimensional matrix calculations during forward and backward propagation, thereby enhancing simulation efficiency. This approach reduces execution time by 31.47% in homogeneous cases and 27.91% in heterogeneous cases, while maintaining higher computational accuracy.

Zitieren

APA

Lin, J., Yan, X., Zhang, K., Zhang, Z., & Yao, J. (2025). Anchored Physics-Informed Neural Network for Two-Phase Flow Simulation in Heterogeneous Porous Media. InterPore Journal, 2(3), IPJ250825-5. https://doi.org/10.69631/ipj.v2i3nr67

Vancouver

Lin J, Yan X, Zhang K, Zhang Z, Yao J. Anchored Physics-Informed Neural Network for Two-Phase Flow Simulation in Heterogeneous Porous Media. InterPore Journal. 2025;2(3):IPJ250825-5. doi:10.69631/ipj.v2i3nr67

BibTeX
@article{Lin2025,
  author = {Lin, Jingqi and Yan, Xia and Zhang, Kai and Zhang, Zhao and Yao, Jun},
  title = {Anchored Physics-Informed Neural Network for Two-Phase Flow Simulation in Heterogeneous Porous Media},
  journal = {InterPore Journal},
  year = {2025},
  volume = {2},
  number = {3},
  pages = {IPJ250825--5},
  doi = {10.69631/ipj.v2i3nr67}
}
Kostenlos starten →