Anomaly detection method for geological hazard time-series data based on multi-source data fusion

To improve the integrity of geological hazard time-series data and enhance the accuracy of anomaly detection, a multi-source data fusion method for anomaly detection of geological hazard time-series data is proposed. The uncertainty of multi-source data fusion for geological hazards is quantified through D-S evidence theory to obtain fusion results. A geological hazard time-series data anomaly detection model is constructed, including anomaly models and incremental learning modules, using autoencoders, graph attention networks, and gated recurrent units to capture feature correlations and temporal characteristics. The model identifies anomalies through reconstruction error, multi-head attention mechanism, and gating mechanism, calculates the root mean square error as the anomaly score, and compares it with the preset value to determine anomalies. Test results indicate that the data integrity of the proposed method consistently remains above 90%, and the highest anomaly detection accuracy reaches 98.45%.