skip to main content

Title: ARRU Phase Picker: Attention Recurrent-Residual U-Net for Picking Seismic P - and S -Phase Arrivals
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 more » 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. « less
; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
Seismological Research Letters
Page Range or eLocation-ID:
2410 to 2428
Sponsoring Org:
National Science Foundation
More Like this
  1. 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 activitymore »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.« less
  2. Abstract

    We derive new, 3D, isotropic models of seismic compressional and shear wavespeeds, Vp and Vs, respectively, their ratio, Vp/Vs, and a catalog of relocated earthquakes for Southern California from more than 10 million P‐ and S‐wave arrivals associated with over 0.3 million earthquakes that occurred between 2000 and 2020. We augment high‐quality analyst‐reviewed phase arrival picks from the Southern California Earthquake Data Center with S‐wave arrival picks obtained with an automated algorithm, and we derive new wavespeed models via traveltime tomography formulated using Poisson‐Voronoi cells (Fang et al., 2020, The results contribute to improved regional wavespeed models, particularly the Vp/Vs model, and absolute event locations. The obtained models correlate well with regional geological features and yield more accurate synthetic waveforms than other regional models do for waves with periods shorter than 5 s in much of the modeled region. The derived event catalog exhibits tighter spatial clustering than the standard regional catalog, thereby helping to characterize subsurface features of major faults. The regional 1D averaged Vp/Vs ratio shows high values at shallow depths, decreases to a minimum at about 10 km, then increases again at greater depths below 15 km. Deep seismicity correlates well with regions of Vp/Vs ratio lower than 1.75,more »which may indicate an increased brittle‐to‐ductile transition depth with an important influence on crustal mechanics. The new wavespeed models and seismic catalog can be useful for various studies including analyses of seismicity patterns and simulations of crustal deformation and ground motion.

    « less
  3. Abstract The Alaska Amphibious Community Seismic Experiment (AACSE) comprised 75 ocean-bottom seismometers and 30 land stations and covered about 650 km along the segment of the subduction zone that includes Kodiak Island, the Alaska Peninsula and the Shumagin Islands between May 2018 and September 2019. This unprecedented onshore-offshore dataset provided an opportunity to compile a greatly enhanced earthquake catalog for the region by both increasing the number of detected earthquakes and improving the accuracy of their source parameters. We use all available regional and AACSE campaign seismic data to compile an earthquake catalog for the region between Kodiak and the Shumagin Islands including the Alaska Peninsula (51° N–59° N, 148° W–163° W). We apply the same processing and reporting standards to additional picks and events as the Alaska Earthquake Center currently uses for compilation of the authoritative regional earthquake catalog. Over 7200 events (both newly detected and previously reported) have been processed with AACSE data. We added about 30% more events, 60% more phase picks, lowered the magnitude of completeness by about 0.2 on average across the region, and improved location errors. All data have been published in public data archives. In addition, we test the machine-learning earthquake detection and picking algorithm EarthquakeTransformer (EQT) onmore »the AACSE seismic dataset, comparing EQT-determined P and S picks with the new catalog. EQT is entirely trained on land data, whereas AACSE is amphibious. Overall, EQT finds 59% of P and 63% of S arrivals in the catalog within 300 km epicentral distance. The percent of catalog picks detected by EQT varies inversely with earthquake epicentral distance, and EQT performs particularly poorly on data from earthquakes recorded by instruments in the outer rise.« less
  4. Abstract

    Recent progresses in artificial intelligence and machine learning make it possible to automatically identify seismic phases from exponentially growing seismic data. Despite some exciting successes in automatic picking of the first P‐ and S‐wave arrivals, auto‐identification of later seismic phases such as the Moho‐reflected PmP waves remains a significant challenge in matching the performance of experienced analysts. The main difficulty of machine‐identifying PmP waves is that the identifiable PmP waves are rare, making the problem of identifying the PmP waves from a massive seismic database inherently unbalanced. In this work, by utilizing a high‐quality PmP data set (10,192 manual picks) in southern California, we develop PmPNet, a deep‐neural‐network‐based algorithm to automatically identify PmP waves efficiently; by doing so, we accelerate the process of identifying the PmP waves. PmPNet applies similar techniques in the machine learning community to address the unbalancement of PmP datasets. The architecture of PmPNet is a residual neural network (ResNet)‐autoencoder with additional predictor block, where encoder, decoder, and predictor are equipped with ResNet connection. We conduct systematic research with field data, concluding that PmPNet can efficiently achieve high precision and high recall simultaneously to automatically identify PmP waves from a massive seismic database. Applying the pre‐trainedmore »PmPNet to the seismic database from January 1990 to December 1999 in southern California, we obtain nearly twice more PmP picks than the original PmP data set, providing valuable data for other studies such as mapping the topography of the Moho discontinuity and imaging the lower crust structures of southern California.

    « less
  5. SUMMARY A fleet of autonomously drifting profiling floats equipped with hydrophones, known by their acronym mermaid, monitors worldwide seismic activity from inside the oceans. The instruments are programmed to detect and transmit acoustic pressure conversions from teleseismic P wave arrivals for use in mantle tomography. Reporting seismograms in near-real time, within hours or days after they were recorded, the instruments are not usually recovered, but if and when they are, their memory buffers can be read out. We present a unique 1-yr-long data set of sound recorded at frequencies between 0.1 and 20 Hz in the South Pacific around French Polynesia by a mermaid float that was, in fact, recovered. Using time-domain, frequency-domain and time-frequency-domain techniques to comb through the time-series, we identified signals from 213 global earthquakes known to published catalogues, with magnitudes 4.6–8.0, and at epicentral distances between 24° and 168°. The observed signals contain seismoacoustic conversions of compressional and shear waves travelling through crust, mantle and core, including P, S, Pdif, Sdif, PKIKP, SKIKS, surface waves and hydroacoustic T phases. Only 10 earthquake records had been automatically reported by the instrument—the others were deemed low-priority by the onboard processing algorithm. After removing all seismic signals from the record,more »and also those from other transient, dominantly non-seismic, sources, we are left with the infrasonic ambient noise field recorded at 1500 m depth. We relate the temporally varying noise spectral density to a time-resolved ocean-wave model, WAVEWATCH III. The noise record is extremely well explained, both in spectral shape and in temporal variability, by the interaction of oceanic surface gravity waves. These produce secondary microseisms at acoustic frequencies between 0.1 and 1 Hz according to the well-known frequency-doubling mechanism.« less