EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of an Intelligent Identification Model for Mine Water Inrush Sources in Karst Mining Areas Based on Multi-Source Data Fusion and a KPCA-ISSA-SVM Framework

Xiang He, Xun Zhou, Zheming Shi, Fengji Yang, Boqiang Xue, Tong Zhang, Xuelan Dong, Chao Yang

Water · 08.05.2026 · 18 (10) · 1122

DOI: 10.3390/w18101122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 08.05.2026. Verfasst von Xiang He und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Geology and Mineral Group Co., Ltd. Xiang He Expert Studio.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of identifying mine water inrush sources and the low efficiency of risk control under complex karst hydrogeological conditions in the Beiya Gold Mine, Yunnan, this study proposes an intelligent identification model integrating nonlinear feature extraction and intelligent parameter optimization. Utilizing 42 sets of measured water samples (comprising karst springs, surface water, and solution caves), a coupling identification model was constructed based on 11-dimensional features including hydrochemical indices and hydrogen–oxygen isotopes. The model employs Kernel Principal Component Analysis (KPCA) to extract discriminative low-dimensional features from nonlinear data, while the critical parameters of the Support Vector Machine (SVM) are optimized via an Improved Sparrow Search Algorithm (ISSA) to enhance generalization performance. The results demonstrate that the following: (1) the proposed model achieves an identification accuracy of 91.7% on the independent test set, significantly outperforming benchmark models such as RF and standard SVM; (2) three sets of comparative experiments indicate that the fusion of multi-source features yields superior identification performance compared to single-source inputs; and (3) SHAP (shapley additive explanation) interpretability analysis reveals that HCO3−, Mg2+, Ca2+, and F− are the core discriminative factors, with their contribution patterns aligning closely with the hydrogeochemical evolution mechanisms of the mining area. This model achieves a synergy between high-precision identification and mechanical interpretability, providing reliable technical support for water disaster prevention in karst mining areas.

Förderung

  • Yunnan Geology and Mineral Group Co., Ltd. Xiang He Expert Studio

Zitieren

APA

He, X., Zhou, X., Shi, Z., Yang, F., Xue, B., Zhang, T., Dong, X., & Yang, C. (2026). Development of an Intelligent Identification Model for Mine Water Inrush Sources in Karst Mining Areas Based on Multi-Source Data Fusion and a KPCA-ISSA-SVM Framework. Water, 18(10), 1122. https://doi.org/10.3390/w18101122

Vancouver

He X, Zhou X, Shi Z, Yang F, Xue B, Zhang T, et al. Development of an Intelligent Identification Model for Mine Water Inrush Sources in Karst Mining Areas Based on Multi-Source Data Fusion and a KPCA-ISSA-SVM Framework. Water. 2026;18(10):1122. doi:10.3390/w18101122

BibTeX
@article{He2026,
  author = {He, Xiang and Zhou, Xun and Shi, Zheming and Yang, Fengji and Xue, Boqiang and Zhang, Tong and Dong, Xuelan and Yang, Chao},
  title = {Development of an Intelligent Identification Model for Mine Water Inrush Sources in Karst Mining Areas Based on Multi-Source Data Fusion and a KPCA-ISSA-SVM Framework},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1122},
  doi = {10.3390/w18101122}
}
Kostenlos starten →