Abstract
Seismic data obtained from seismic stations are the major source of the information used to forecast earthquakes. With the growth in the number of seismic stations, the size of the dataset has also increased. Traditionally, STA/LTA and AIC method have been applied to process seismic data. However, the enormous size of the dataset reduces accuracy and increases the rate of missed detection of the P and S wave phase when using these traditional methods. To tackle these issues, we introduce the novel U-net-Bidirectional Long-Term Memory Deep Network (UBDN) which can automatically and accurately identify the P and S wave phases from seismic data. The U-net based UBDN strongly maintains the U-net’s high accuracy in edge detection for extracting seismic phase features. Meanwhile, it also reduces the missed detection rate by applying the Bidirectional Long Short-Term Memory (Bi-LSTM) mode that processes timing signals to establish the relationship between seismic phase features. Experimental results using the Stanford University seismic dataset and data from the 2008 Wenchuan earthquake aftershock confirm that the proposed UBDN method is very accurate and has a lower rate of missed phase detection, outperforming solutions that adapt traditional methods by an order of magnitude in terms of error percentage.
Highlights
Seismic phase identification is a solid foundation for earthquake prevention and disaster reduction work
To address the limitations in the application of U-net models to seismic phase autoidentification, we propose in this paper a novel U-net Bidirectional Long-Term
In order to objectively evaluate the performance of the U-net29 Bidirectional Long-Term Memory Deep Network (UBDN) model in practical applications and ensure the reliability of the experimental results, we used the calculation of the root mean square error (RMSE), accuracy (A), and missed detection rate (M) of the different methods
Summary
Seismic phase identification is a solid foundation for earthquake prevention and disaster reduction work (e.g., earthquake early warning systems). Manual identification and travel timetable-based calculations were the two main methods used to analyze various seismic phase data and identify seismic phases. With the growth in the number of seismic stations, the amount of seismic data available has increased significantly. The efficiency and accuracy of manual identification has gradually decreased. The noise pollution caused by urbanization leads to higher rates of missed detection of low-level earthquakes. Manual identification can no longer maintain the accuracy and efficiency of phase detection
Submitted Version (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have