CNN-LSTM for Roof-Water-Inrush Risk Zoning with Edge Deployment
Water · 17.07.2026 · 18 (14) · 1739
DOI: 10.3390/w18141739 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water, online erschienen am 17.07.2026. Verfasst von Tao Yang und 7 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reliable roof-water-inrush risk zoning in coal mines remains difficult under small-sample conditions because geological, hydrogeological, and mining-induced factors interact nonlinearly, and field labels are often derived from engineering evidence rather than complete accident records. This study aims to develop and preliminarily validate a deployment-oriented workflow for case-specific roof-water-inrush risk-zone classification in the No. 4−3 coal seam of Shiyangou Coal Mine, Shaanxi Province, China. A total of 100 spatial evaluation samples were compiled using eight indicators grouped into water-resisting capacity, water-supply intensity, water-conducting pathways, mining-induced disturbance, and rock-mass integrity. The Safe-Zone and Risk-Zone labels were generated from mine-water-prevention documents, borehole and hydrogeological evidence, abnormal goaf-water information, and expert engineering judgment. A lightweight CNN-LSTM model was trained with leakage-controlled data splitting, early stopping, L2 regularization, gradient clipping, and model-capacity control. Because the inputs are static or quasi-static spatial indicators, LSTM was used only as a gated feature-dependency module for CNN-derived feature sequences, and its necessity was examined using ablation and feature-order perturbation tests. In repeated stratified five-fold cross-validation, the model achieved mean accuracy, F1-score, and AUC values of 0.792 ± 0.108, 0.633 ± 0.111, and 0.829 ± 0.097, respectively. On an independent prediction dataset, the accuracy and AUC were 0.750 and 0.743, respectively. After ONNX export, STM32CubeMX evaluation indicated 68,962 B Flash and 3252 B RAM consumption. These results indicate the preliminary feasibility of embedded roof-water-inrush risk-zone classification for this specific mine case. However, the findings do not demonstrate cross-mine transferability; further validation using external datasets, independent labels, and field deployment records is required.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, T., Wang, Q., Zhang, J., Liu, D., Lin, H., Zhang, Y., Zhang, L., & Zhang, S. (2026). CNN-LSTM for Roof-Water-Inrush Risk Zoning with Edge Deployment. Water, 18(14), 1739. https://doi.org/10.3390/w18141739
Vancouver
Yang T, Wang Q, Zhang J, Liu D, Lin H, Zhang Y, et al. CNN-LSTM for Roof-Water-Inrush Risk Zoning with Edge Deployment. Water. 2026;18(14):1739. doi:10.3390/w18141739
BibTeX
@article{Yang2026,
author = {Yang, Tao and Wang, Quanxin and Zhang, Jie and Liu, Dong and Lin, Haifei and Zhang, Yiming and Zhang, Longqian and Zhang, Shuqi},
title = {CNN-LSTM for Roof-Water-Inrush Risk Zoning with Edge Deployment},
journal = {Water},
year = {2026},
volume = {18},
number = {14},
pages = {1739},
doi = {10.3390/w18141739}
}
EUVIMED