Seismic phase association is a fundamental task in seismology that pertains to linking together phase detections on different sensors that originate from a common earthquake. It is widely employed to detect earthquakes on permanent and temporary seismic networks and underlies most seismicity catalogs produced around the world. This task can be challenging because the number of sources is unknown, events frequently overlap in time, or can occur simultaneously in different parts of a network. We present PhaseLink, a framework based on recent advances in deep learning for grid‐free earthquake phase association. Our approach learns to link phases together that share a common origin and is trained entirely on millions of synthetic sequences of
- Award ID(s):
- 1759810
- NSF-PAR ID:
- 10129287
- Date Published:
- Journal Name:
- Seismological Research Letters
- Volume:
- 90
- Issue:
- 6
- ISSN:
- 0895-0695
- Page Range / eLocation ID:
- 2276 to 2284
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract P andS wave arrival times generated using a 1‐D velocity model. Our approach is simple to implement for any tectonic regime, suitable for real‐time processing, and can naturally incorporate errors in arrival time picks. Rather than tuning a set of ad hoc hyperparameters to improve performance, PhaseLink can be improved by simply adding examples of problematic cases to the training data set. We demonstrate the state‐of‐the‐art performance of PhaseLink on a challenging sequence from southern California and synthesized sequences from Japan designed to test the point at which the method fails. For the examined data sets, PhaseLink can precisely associate phases to events that occur only ∼12 s apart in origin time. This approach is expected to improve the resolution of seismicity catalogs, add stability to real‐time seismic monitoring, and streamline automated processing of large seismic data sets. -
more » « less
Abstract Seven three‐component ocean bottom seismometers (OBS) of the Ocean Observatories Initiative (OOI) Cabled Array on top of Axial Seamount are continuously streaming data in real time to the Incorporated Research Institutions for Seismology (IRIS). The OBS array records earthquakes from the submarine volcano which last erupted on 24 April 2015, about 4 months after the array came online. The OBS data have proven crucial in providing insight into the volcano structure and dynamics (Wilcock et al., 2016,
https://doi.org/10.1126/science.aah5563 ). We implemented a real‐time double‐difference (RT‐DD) monitoring system that automatically computes high‐precision (tens of meters) locations of new earthquakes. The system's underlying double‐difference base catalog includes nearly 100,000 earthquakes and was computed using kurtosis phase onset picks, cross‐correlation phase delay times, and 3‐DP andS velocity models to predict the data. The relocations reveal the fine‐scale structures of long‐lived, narrow (<200 m wide), outward dipping, convex faults on the east and west walls of the caldera that appear to form a figure 8‐shaped ring fault system. These faults accommodate stresses caused by the inflation of magma prior to and deflation during eruptions. The east fault is segmented and pulled apart in east‐west direction due to its interaction with the Juan de Fuca Ridge, which at this location forms an overlapping spreading center. The RT‐DD system enables the monitoring and rapid analysis of variations in fine‐scale seismic and fault properties and has the potential to improve prediction of timing and location of the next Axial eruption expected to occur in the 2022–2023 time frame. -
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.more » « less
-
more » « less
Abstract We develop an automated processing procedure to derive a new catalog of earthquake locations, magnitudes, and potencies and analyze 9 years of data between 2008 and 2016 in the San Jacinto fault‐zone region. Our procedure accounts for detailed 3‐D velocity structure using a probabilistic global‐search location inversion and obtains high‐precision relative event locations using differential travel times measured by cross‐correlating waveforms. The obtained catalog illuminates spatiotemporal seismicity patterns in the fault zone with observations for 108,800 earthquakes in the magnitude range −1.8 to 5.4. Inside a focus region consisting of an 80‐km by 50‐km rectangle oriented parallel to the main fault trace, we estimate a 99% detection rate of earthquakes with magnitude 0.6 and greater and detect and locate about 60% more events than those present in the Southern California Seismic Network catalog. The results provide the most complete catalog available for the focused study region during the analyzed period and include both deeper events and very shallow patches of seismicity not present in the regional catalog. The seismicity exhibits a variety of complex patterns that contain important information on deformation processes in the region. The fraction of event pairs with waveforms having cross‐correlation coefficients ≥0.95 is only about 3%, indicating diverse processes operating in the fault zone.
-
null (Ed.)Abstract Seismograms are convolution results between seismic sources and the media that seismic waves propagate through, and, therefore, the primary observations for studying seismic source parameters and the Earth interior. The routine earthquake location and travel-time tomography rely on accurate seismic phase picks (e.g., P and S arrivals). As data increase, reliable automated seismic phase-picking methods are needed to analyze data and provide timely earthquake information. However, most traditional autopickers suffer from low signal-to-noise ratio and usually require additional efforts to tune hyperparameters for each case. In this study, we proposed a deep-learning approach that adapted soft attention gates (AGs) and recurrent-residual convolution units (RRCUs) into the backbone U-Net for seismic phase picking. The attention mechanism was implemented to suppress responses from waveforms irrelevant to seismic phases, and the cooperating RRCUs further enhanced temporal connections of seismograms at multiple scales. We used numerous earthquake recordings in Taiwan with diverse focal mechanisms, wide depth, and magnitude distributions, to train and test our model. Setting the picking errors within 0.1 s and predicted probability over 0.5, the AG with recurrent-residual convolution unit (ARRU) phase picker achieved the F1 score of 98.62% for P arrivals and 95.16% for S arrivals, and picking rates were 96.72% for P waves and 90.07% for S waves. The ARRU phase picker also shown a great generalization capability, when handling unseen data. When applied the model trained with Taiwan data to the southern California data, the ARRU phase picker shown no cognitive downgrade. Comparing with manual picks, the arrival times determined by the ARRU phase picker shown a higher consistency, which had been evaluated by a set of repeating earthquakes. The arrival picks with less human error could benefit studies, such as earthquake location and seismic tomography.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1785/0220190052
