EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving a Prediction Model for Tunnel Water Inflow Estimation Using LSTM and Bayesian Optimization

Zhen Huang, Zishuai Yang, Yun Wu, Lijian Ma, Tao Sun, Zhenpeng Wang, Kui Zhao, Xiaojun Zhang, Haigang Li, Yu Zheng

Water · 23.10.2025 · 17 (21) · 3045

DOI: 10.3390/w17213045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 23.10.2025. Verfasst von Zhen Huang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Jiangxi Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Water inrush and mud burst disasters pose severe challenges to the safe and efficient construction of underground engineering. Water inflow prediction is closely related to drainage design, disaster prevention and control, and the safety of the surrounding ecological environment. Thus, assessing the water inflow accurately is of importance. This study proposes a Bayesian Optimization-Long Short-Term Memory (BOA-LSTM) recurrent neural network for predicting tunnel water inflow. The model is based on four input parameters, namely tunnel depth (H), groundwater level (h), rock quality designation (RQD), and water-richness (W), with water inflow (WI) as the single-output variable. The model first processes and analyzes the data, quantitatively characterizing the correlations between input parameters. The tunnel water inflow is predicted using the long short-term memory (LSTM) recurrent neural network, and the Bayesian optimization algorithm (BOA) is employed to select the hyperparameters of the LSTM, primarily including the number of hidden layer units, initial learning rate, and L2 regularization coefficient. The modeling process incorporates a five-fold cross-validation strategy for dataset partitioning, which effectively mitigates overfitting risks and enhances the model’s generalization capability. After a comprehensive comparison among a series of machine learning models, including a long short-term memory recurrent neural network (LSTM), random forest (RF), back propagation neural network (BP), extreme learning machine (ELM), radial basis function neural network (RBFNN), least squares support vector machine (LIBSVM), and convolutional neural network (CNN), BOA-LSTM performed excellently. The proposed BOA-LSTM model substantially surpasses the standard LSTM and other comparative models in tunnel water inflow prediction, demonstrating superior performance in both accuracy and generalization. Hence, it provides a reference basis for tunnel engineering water inflow prediction.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Jiangxi Provincial Natural Science Foundation
  • Program of Qingjiang Excellent Young Talents, Jiangxi University of Science and Technology
  • National Key Laboratory of Geological Disaster Prevention and Geological Environment Protection

Zitieren

APA

Huang, Z., Yang, Z., Wu, Y., Ma, L., Sun, T., Wang, Z., Zhao, K., Zhang, X., Li, H., & Zheng, Y. (2025). Improving a Prediction Model for Tunnel Water Inflow Estimation Using LSTM and Bayesian Optimization. Water, 17(21), 3045. https://doi.org/10.3390/w17213045

Vancouver

Huang Z, Yang Z, Wu Y, Ma L, Sun T, Wang Z, et al. Improving a Prediction Model for Tunnel Water Inflow Estimation Using LSTM and Bayesian Optimization. Water. 2025;17(21):3045. doi:10.3390/w17213045

BibTeX
@article{Huang2025,
  author = {Huang, Zhen and Yang, Zishuai and Wu, Yun and Ma, Lijian and Sun, Tao and Wang, Zhenpeng and Zhao, Kui and Zhang, Xiaojun and Li, Haigang and Zheng, Yu},
  title = {Improving a Prediction Model for Tunnel Water Inflow Estimation Using LSTM and Bayesian Optimization},
  journal = {Water},
  year = {2025},
  volume = {17},
  number = {21},
  pages = {3045},
  doi = {10.3390/w17213045}
}
Kostenlos starten →