An Enhanced Osprey Optimization-Based Interpretable Deep Learning Framework for Predicting Coal Spontaneous Combustion Temperatures
Rui Yan1, Botao Fan2, Xueqi Qu2, Cuihuan Ren1,*, Xu Zhou1,*
1 College of Science, North China University of Science and Technology, Tangshan, China
2 School of Emergency Management and Safety Engineering, North China University of Science and Technology, Tangshan, China
* Corresponding Author: Cuihuan Ren. Email: 
; Xu Zhou. Email: 
Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.085749
Received 17 May 2026; Accepted 24 June 2026; Published online 10 July 2026
Abstract
Accurate prediction of coal spontaneous combustion (CSC) temperatures is crucial for safe coal mine production. To further improve the accuracy of CSC temperature prediction and the interpretability of the model, this study proposes an interpretable Chebyshev chaotic mapping-Lévy flight-Enhanced pinhole imaging inverse learning-Adaptive weighted Osprey Optimization Algorithm optimized Bidirectional Long Short-Term Memory (CLEA-OOA-BiLSTM) framework for predicting CSC temperatures. First, we optimized the Osprey Optimization Algorithm (OOA) by incorporating the Chebyshev chaotic map, Lévy flights, enhanced pinhole imaging backpropagation, and an adaptive weighting strategy, thereby developing the CLEA-OOA algorithm. Through comparative experiments using eight benchmark test functions and four heuristic algorithms, we verified that CLEA-OOA achieves superior convergence accuracy and convergence speed. Subsequently, using data from the Dongtan Coal Mine as the subject of study, we employed CLEA-OOA to perform adaptive optimization of the BiLSTM hyperparameters. Using Spearman’s correlation analysis, C
2H
4/C
2H
6, CO, C
2H
4, CO/ΔO
2, and O
2 (%) were identified as key indicators for predicting the CSC temperatures. The results show that the CLEA-OOA-BiLSTM model achieves an R
2 of 0.98, which is higher than that of all comparison models. The model’s MSE, RMSE, MAE, and MAPE are 11.26%, 3.36%, 2.73%, and 2.74%, respectively, demonstrating the model’s excellent error control capabilities. The results of the global and local SHapley Additive exPlanations (SHAP) interpretability analysis indicate that C
2H
4/C
2H
6 and CO are key contributing factors to the model’s decision-making, consistent with the oxidation mechanisms of CSC. The model was validated using coal mine data from multiple locations in Inner Mongolia, Shanxi, and Anhui, with R
2 consistently reaching 0.985, demonstrating strong cross-regional generalization capabilities and practical engineering value. This framework provides a new method for CSC early warning and the intelligent development of mines.
Keywords
Coal spontaneous combustion; coal mine safety; interpretable deep learning; temperature prediction; BiLSTM; improved osprey optimization algorithm; SHAP analysis
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
