CSESnet: A deep learning P-wave detection model based on UNet plus plus designed for China Seismic Experimental Site

Accurate detection of P-wave arrivals has important applications in real-time seismic data processing, such as earthquake monitoring and earthquake early warning. The Sichuan and Yunnan regions, where the China Seismic Experimental Site (CSES) is located, has frequent strong earthquakes and large amount small earthquakes, resulting in serious earthquake disasters. In this paper, we modify the UNet++ network structure and use 490,000 event waveform data and 78,000 noisy data from the CSES as the data set, and analyze the effects of the training set quality, labeled data and loss function on the model performance to obtain a new P-wave detection model-CSESnet. The recall, precision and F1 score of this model are 94.6%, 85.4% and 89.7%, respectively. The tests in Beijing Capital Circle (BCC) indicates the performance of the CSESnet decrease little and has good generalization. The test in Luxian M6.0 earthquake shows that CSESnet can also predict the P-wave arrival times of large earthquakes and process strong motion data very well. CSESnet provides a new detection model to improve the earthquake detection capability in CSES.

Automated summary

In this paper, a new P-wave detection model called CSESnet is proposed by modifying the UNet++ network structure and using a dataset consisting of 490,000 event waveform data and 78,000 noisy data from the China Seismic Experimental Site (CSES). The model achieves recall, precision, and F1 scores of 94.6%, 85.4%, and 89.7%, respectively. Tests conducted in the Beijing Capital Circle (BCC) show that CSESnet has good generalization and little decrease in performance. Additionally, the model is also able to accurately predict the P-wave arrivals and process strong motion data of large earthquakes, as demonstrated in the Luxian M6.0 earthquake test. The findings suggest that CSESnet provides a new detection model to enhance earthquake detection capability in CSES.