A Pattern Recognition Algorithm for AETA Original Geoacoustic Data Anomaly Detection

We found a kind of anomalous waveform that appeared frequently before and after the earthquake based on AETA original geoacoustic data. To capture these abnormal geoacoustic signals, we designed a pattern recognition algorithm and transformed original geoacoustic data into anomalous eigenvalues. In this paper, we selected original geoacoustic data for five AETA stations in 2018 as the research object. Through the above-mentioned algorithm, we got the anomalous eigenvalues of the five AETA stations and then contrasted analysis with seismic events around the station that met the conditions of magnitude and shock time. Experiment results show, there is a clear correlation between surrounding seismic events and the anomalous eigenvalues extracted from the original geoacoustic data of the pattern recognition algorithm proposed in this paper.