No abstract

Research of seismic infrared remote sensing has been undertaken for several decades, but there is no stable and effective earthquake prediction method. A new algorithm combining the long short-term memory and the density-based spatial clustering of applications with noise models is proposed to extract the anomalies from the multichannel infrared remote sensing images of the Fengyun-4 satellites. A statistical analysis is used to validate the correlation between the anomalies and earthquakes. The results show that the correlation rate is 64.29%, the hit rate is 68.75%, and the probability gain is about 1.91. In the Madoi and YangBi earthquake cases, the infrared anomaly detected in this paper is correlated with the TEC anomaly found in the previous research. This indicates that it is feasible to combine multi-source data to improve the accuracy of earthquake prediction in future studies.

No abstract

Earthquake prediction by using total electron content is a commonly used seismic research method. The long short-term memory model is a kind of method to predict time series and has been used for the prediction of total electron content, and the relative power spectrum method is one of the pre-seismic infrared anomaly detection algorithms in the frequency domain. In this paper, a new method combining these two algorithms is used to extract abnormal signals; thus scientists can more easily detect anomalies of total electron content similar to those before the Qinghai and Yunnan earthquakes happened on 21 May 2021. There are pre-seismic anomalies with the high-value relative power spectrum near two epicenters. To validate the correlation between anomalies and earthquakes statistically, the spatiotemporal characteristics of TEC anomalies are analyzed based on connected region recognition. Then, the proportion of earthquake-related anomalies (the correlation rate), the proportion of earthquakes outside the predicted range (the miss rate), and the ratio of the proportion of earthquakes within the predicted range to the spatiotemporal occupancy of anomalies, which is called the probability gain, were used to assess the method. The appropriate parameters of the algorithm for the miss rate below 50% were searched. The highest probability gain is 1.91, which means anomalies of total electron content may decrease the uncertainty of earthquake prediction.