Multimodal Fusion Interpolation Method for Missing Monitoring Data in Deep-Buried Tunnel Rockburst Prediction

Missing monitoring data reduce the reliability of rockburst early warning in deep-buried tunnel engineering. This study proposes a multimodal fusion interpolation framework that combines LSTM-based temporal estimation, Pearson’s/Spearman’s/MIC correlation analysis, and Whale Optimization Algorithm (WOA)-based weight allocation for missing monitoring indicators. A case dataset containing 251 consecutive samples from one tunnel in southwestern China was used to examine the engineering feasibility of the method. The interpolated data were further used in GRU, CNN-LSTM, N-BEATS, and deep fully connected prediction models. The results indicate that the interpolated dataset improves downstream rockburst prediction in this case study. Because the dataset is limited to one tunnel project, the conclusions are now restricted to similar deep-buried tunnel conditions and should not be interpreted as universal proof of superiority.