Beyond Static Fingerprints to Dynamic Evolution: A CNN–LSTM–Attention Model for Identifying Coal Mine Water Inrush Sources in Northern China

Mine water inrush poses a severe threat to coal mine safety, making rapid and accurate identification of water sources essential. Existing methods, including conventional hydrochemical diagrams and machine learning, struggle with high-dimensional, nonlinear hydrogeochemical data characterized by implicit temporal dynamics. This study proposes an intelligent identification model integrating convolutional neural networks (CNNs), long short-term memory (LSTM), and an attention mechanism (CNN–LSTM–Attention). The model employs a CNN to extract local fingerprint features from hydrochemical indicators (K++Na+, Ca2+, Mg2+, Cl−, SO42−, and HCO3−), uses LSTM to model evolutionary patterns, and leverages an attention mechanism to adaptively focus on critical discriminative features. Based on 76 water samples from the Tangjiahui Coal Mine, the model achieved 91% accuracy on the test set, outperforming standalone CNN, LSTM, and CNN–LSTM models. Visualization of attention weights further revealed key diagnostic indicators, enhancing interpretability and bridging data-driven methods with hydrogeochemical mechanisms. This study provides a powerful and interpretable tool for water inrush source identification, supporting the transition toward intelligent and transparent coal mine water hazard prevention.