EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Physics-Informed Neural Networks for Deep Tunnel Seepage Field Prediction: A Bayesian Optimization Approach

Yiheng Pan, Yongqi Zhang, Qiyuan Lu, Peng Xia, Jiarui Qi, Qiqi Luo

Water · 04.09.2025 · 17 (17) · 2621

DOI: 10.3390/w17172621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 04.09.2025. Verfasst von Yiheng Pan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Fujian.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting tunnel seepage field is a critical challenge in the construction of underground engineering projects. While traditional analytical solutions and numerical methods struggle with complex geometric boundaries, standard Physics-Informed Neural Networks (PINNs) encounter additional challenges in tunnel seepage problems, including training instability, boundary handling difficulties, and low sampling efficiency. This paper develops an enhanced PINN framework designed specifically for predicting tunnel seepage field by integrating Exponential Moving Average (EMA) weight stabilization, Residual Adaptive Refinement with Distribution (RAR-D) sampling, and Bayesian optimization for collaborative training. The framework introduces a trial function method based on an approximate distance function (ADF) to address the precise handling of circular tunnel boundaries. The results demonstrate that the enhanced PINN framework achieves an exceptional prediction accuracy with an overall average relative error of 5 × 10−5. More importantly, the method demonstrates excellent practical applicability in data-scarce scenarios, maintaining acceptable prediction accuracy even when monitoring points are severely limited. Bayesian optimization reveals the critical insight that loss weight configuration is more important than network architecture in physics-constrained problems. This study is a systematic application of PINNs to prediction of tunnel seepage field and holds significant value for tunnel construction monitoring and risk assessment.

Förderung

  • Natural Science Foundation of Fujian

Zitieren

APA

Pan, Y., Zhang, Y., Lu, Q., Xia, P., Qi, J., & Luo, Q. (2025). Enhanced Physics-Informed Neural Networks for Deep Tunnel Seepage Field Prediction: A Bayesian Optimization Approach. Water, 17(17), 2621. https://doi.org/10.3390/w17172621

Vancouver

Pan Y, Zhang Y, Lu Q, Xia P, Qi J, Luo Q. Enhanced Physics-Informed Neural Networks for Deep Tunnel Seepage Field Prediction: A Bayesian Optimization Approach. Water. 2025;17(17):2621. doi:10.3390/w17172621

BibTeX
@article{Pan2025,
  author = {Pan, Yiheng and Zhang, Yongqi and Lu, Qiyuan and Xia, Peng and Qi, Jiarui and Luo, Qiqi},
  title = {Enhanced Physics-Informed Neural Networks for Deep Tunnel Seepage Field Prediction: A Bayesian Optimization Approach},
  journal = {Water},
  year = {2025},
  volume = {17},
  number = {17},
  pages = {2621},
  doi = {10.3390/w17172621}
}
Kostenlos starten →