Toward Fully Autonomous Seismic Networks: Backprojecting Deep Learning-Based Phase Time Functions for Earthquake Monitoring on Continuous Recordings

Abstract

Accurate and (near) real-time earthquake monitoring provides the spatial and temporal behaviors of earthquakes for understanding the nature of earthquakes, and also helps in regional seismic hazard assessments and mitigations. Because of the increase in both the quality and quantity of seismic data, an automated earthquake monitoring system is needed. Most of the traditional methods for detecting earthquake signals and picking phases are based on analyses of features in recordings of an individual earthquake and/or their differences from background noises. When seismicity is high, the seismograms are complicated, and, therefore, traditional analysis methods often fail. With the development of machine learning algorithms, earthquake signal detection and seismic phase picking can be more accurate using the features obtained from a large amount of earthquake recordings. We have developed an attention recurrent residual U-Net algorithm, and used data augmentation techniques to improve the accuracy of earthquake detection and seismic phase picking on complex seismograms that record multiple earthquakes. The use of probability functions of P and S arrivals and potential P and S arrival pairs of earthquakes can increase the computational efficiency and accuracy of backprojection for earthquake monitoring in large areas. We applied our workflow to monitor the earthquake activity in southern California during the 2019 Ridgecrest sequence. The distribution of earthquakes determined by our method is consistent with that in the Southern California Earthquake Data Center (SCEDC) catalog. In addition, the number of earthquakes in our catalog is more than three times that of the SCEDC catalog. Our method identifies additional earthquakes that are close in origin times and/or locations, and are not included in the SCEDC catalog. Our algorithm avoids misidentification of seismic phases for earthquake location. In general, our algorithm can provide reliable earthquake monitoring on a large area, even during a high seismicity period.

Recent advances in earthquake seismology using machine learning

“…Although this approach involves high computation costs, it contributes to detecting small earthquakes with waveforms buried in noise (Li et al 2020a). Compared with characteristic functions, such as STA/LTA (Grigoli et al 2013) or kurtosis (Langet et al 2014) time series used in previous studies, the probability trace estimated using a DL phase picker (Liao et al 2022b) likely significantly reduces the false positive rate. This approach is often adopted in open packages that handle the entire cataloging process from continuous seismic records to hypocenter locations (Zhu et al 2022c;Shi et al 2022).…”

Next Generation Seismic Source Detection by Computer Vision: Untangling the Complexity of the 2016 Kaikōura Earthquake Sequence

“…Waveform-based methods locate sources without first identifying individual seismic phases (Li et al, 2020). In waveform stacking methods, preprocessed waveforms at individual stations are summed along a theoretical travel time curve to generate a time series of brightness images over the study area, with the brightest point in this sequence designated the energy source (McBrearty et al, 2019;Tan et al, 2020;W.-Y. Liao et al, 2022;Li et al, 2020;Dokht et al, 2022).…”

“…Another group of automatic workflows, known as waveform‐based methods, rarely run into phase association ambiguity but can instead suffer from detection and resolution issues (Kao & Shan, 2004; Tan et al., 2020; W.‐Y. Liao et al., 2022). Waveform‐based methods locate sources without first identifying individual seismic phases (Li et al., 2020).…”

“…Another group of automatic workflows, known as waveform-based methods, rarely run into phase association ambiguity but can instead suffer from detection and resolution issues (Kao & Shan, 2004;Tan et al, 2020;W.-Y. Liao et al, 2022).…”

Customization of a deep neural network using local data for seismic phase picking

“…DL pickers can be generalized to other regions or source types that were not used for their training (Mousavi et al, 2020;Liao et al, 2021;Tan et al, 2021;Walter et al, 2021;García et al, 2022;Harsuko and Alkhalifah, 2022;Heck et al, 2022;Liao et al, 2022;Münchmeyer et al, 2022;Wang et al, 2023). However, the performance of the picker is sometimes degraded when applied to those regions or source types (Jiang et al, 2021;Heck et al, 2022;Han et al, 2023).…”