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

• Published in: PloS one Vol. 20; no. 6; p. e0326587
• Main Authors: Yang, Hao, Wang, Tianlong, Fomin, Nikita Igorevich, Xiao, Shuoting, Liu, Liang
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 24.06.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Artificial intelligence; Artificial neural networks; China; Computer and Information Sciences; Debris flow; Deep Learning; Detritus; Earth Sciences; Environmental Monitoring - methods; Epistemology; Errors; Game theory; Geological hazards; Gullies; Machine learning; Mathematical optimization; Mountain regions; Mountainous areas; Neural networks; Neural Networks, Computer; Optimization algorithms; Optimization techniques; Physical Sciences; Predictions; Rainfall; Research and Analysis Methods; Risk assessment; Risk reduction; River basins; Rivers; Rivers - chemistry; Velocity; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0326587

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.