With the continuous development of human society, earthquakes are becoming more and more dangerous to the production and life of human society. Researchers continue to try to predict earthquakes, but the results are still not significant. With the development of data science, sensing and communication technologies, there are increasing efforts to use machine learning methods to predict earthquakes. Our work raises a method that applies big data analysis and machine learning algorithms to earthquakes prediction. All data are accumulated by the Acoustic and Electromagnetic Testing All in One System (AETA). We propose the multi-station Principal Component Analysis (PCA) algorithm and extract features based on this method. At last, we propose a weekly-scale earthquake prediction model, which has a 60% accuracy using LightGBM (LGB).

Acoustic and electromagnetics to artificial intelligence (AETA) is a system used to predict seismic events through monitoring of electromagnetic and geoacoustic signals. It is widely deployed in the Sichuan–Yunnan region (22° N–34° N, 98° E–107° E) of China. Generally, the electromagnetic signals of AETA stations near the epicenter have abnormal disturbances before an earthquake. When a significant decrease or increase in the signal is observed, it is difficult to quantify this change using only visual observation and confirm that it is related to an upcoming large earthquake. Considering that the AETA data comprise a typical time series, current work has analyzed the anomalism of AETA electromagnetic signals using the long short-term memory (LSTM) autoencoder method to prove that the electromagnetic anomaly of the AETA station can be regarded as an earthquake precursor. The results show that there are 2–4% anomalous points and some outliers exceeding 0.7 (after normalization) in the AETA stations within 200 km of the epicenter of the Jiuzaigou earthquake (M. 7.0) and the Yibin earthquake (M. 6.0) half a month before the earthquakes. Therefore, the AETA electromagnetic disturbance signal can be used as an earthquake precursor and for further earthquake prediction.