EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An integrated IKOA-CNN-BiGRU-Attention framework with SHAP explainability for high-precision debris flow hazard prediction in the Nujiang river basin, China

Hao Yang iD, Tianlong Wang iD, Nikita Igorevich Fomin, Shuoting Xiao, Liang Liu

PLOS One · 2025

DOI: 10.1371/journal.pone.0326587 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Hao Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Civil Engineering and Architecture, Ural Federal University, Yekaterinburg, Russia. Hauptthemen laut MEDLINE: Rivers, Neural Networks, Computer. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council, the 1st Doctoral Student Program of the Young Elite Scientists Sponsorship Program by CAST.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Debris flows represent a persistent challenge for disaster prediction in mountainous regions due to their highly nonlinear and multivariate triggering mechanisms. This study proposes an explainable deep learning framework, the Improved Kepler Optimization Algorithm-Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Attention (IKOA-CNN-BiGRU-Attention) model, for precise debris flow hazard prediction in the Yunnan section of the Nujiang River Basin, China. The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. Model explainability is enhanced using SHapley Additive exPlanations (SHAP), which quantify the influence of key factors. The IKOA-CNN-BiGRU-Attention framework consistently outperforms 13 benchmark models, achieving a root mean square error of 2.33 × 10 −6 , mean absolute error of 1.51 × 10 −6 , and mean absolute percentage error of 0.006%. The model maintains high stability across 50 repeated experiments, strong resilience to 20% input noise, and robust generalizability under five-fold cross-validation. Interpretability analysis identifies potential source energy and maximum 24-hour rainfall as primary determinants and uncovers a dual-threshold physical mechanism underlying debris flow initiation. These findings provide a quantitative basis for adaptive early warning and targeted risk mitigation, and establish a transferable framework for explainable geohazard prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RiversNeural Networks, ComputerChinaAlgorithmsDeep LearningEnvironmental Monitoring

Autor:innen und Institutionen

  • Institute of Civil Engineering and Architecture, Ural Federal University, Yekaterinburg, Russia.
  • Ocean College, Zhejiang University, Zhoushan, China.
  • School of Civil and Environmental Engineering, Nanyang Technological University, SingaporeSingapore.

ORCID-Profile: Hao Yang, Tianlong Wang

Förderung

  • China Scholarship Council
  • the 1st Doctoral Student Program of the Young Elite Scientists Sponsorship Program by CAST

Zitieren

APA

Yang, H., Wang, T., Fomin, N. I., Xiao, S., & Liu, L. (2025). An integrated IKOA-CNN-BiGRU-Attention framework with SHAP explainability for high-precision debris flow hazard prediction in the Nujiang river basin, China. PLOS One. https://doi.org/10.1371/journal.pone.0326587

Vancouver

Yang H, Wang T, Fomin NI, Xiao S, Liu L. An integrated IKOA-CNN-BiGRU-Attention framework with SHAP explainability for high-precision debris flow hazard prediction in the Nujiang river basin, China. PLOS One. 2025. doi:10.1371/journal.pone.0326587

BibTeX
@article{Yang2025,
  author = {Yang, Hao and Wang, Tianlong and Fomin, Nikita Igorevich and Xiao, Shuoting and Liu, Liang},
  title = {An integrated IKOA-CNN-BiGRU-Attention framework with SHAP explainability for high-precision debris flow hazard prediction in the Nujiang river basin, China},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0326587}
}
Kostenlos starten →