A data set of earthquake bulletin and seismic waveforms for Ghana obtained by deep learning.

The Ghana Digital Seismic Network (GHDSN) data, with six broadband sensors, operating in southern Ghana for two years (2012-2014). The recorded dataset is processed for simultaneous event detection and phase picking by a Deep Learning (DL) model, the EQTransformer tool. Here, the detected earthquakes consisting of supporting data, waveforms (including P and S arrival phases), and earthquake bulletin are presented. The bulletin includes the 559 arrival times (292 P and 267 S phases) and waveforms of the 73 local earthquakes in SEISAN format. The supporting data encompasses the preliminary crustal velocity models obtained from the joint inversion analysis of the detected hypocentral parameters. These parameters comprised of a 6- layer model of the crustal velocity (Vp and Vp/Vs ratio), incident time sequence, and statistical analysis of the detected earthquakes and hypocentral parameters analyzed and relocated by the updated crustal velocity and graphic representation of them a 3D live figure enlighting the seismogenic depth of the region. This dataset has a unique appeal for earth science specialists to analyze and reprocess the detected waveforms and characterize the seismogenic sources and active faults in Ghana. The metadata and waveforms have been deposited at the Mendeley Data repository [1].

Deep-learning seismology.

Seismic waves from earthquakes and other sources are used to infer the structure and properties of Earth's interior. The availability of large-scale seismic datasets and the suitability of deep-learning techniques for seismic data processing have pushed deep learning to the forefront of fundamental, long-standing research investigations in seismology. However, some aspects of applying deep learning to seismology are likely to prove instructive for the geosciences, and perhaps other research areas more broadly. Deep learning is a powerful approach, but there are subtleties and nuances in its application. We present a systematic overview of trends, challenges, and opportunities in applications of deep-learning methods in seismology.

Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking.

Earthquake signal detection and seismic phase picking are challenging tasks in the processing of noisy data and the monitoring of microearthquakes. Here we present a global deep-learning model for simultaneous earthquake detection and phase picking. Performing these two related tasks in tandem improves model performance in each individual task by combining information in phases and in the full waveform of earthquake signals by using a hierarchical attention mechanism. We show that our model outperforms previous deep-learning and traditional phase-picking and detection algorithms. Applying our model to 5 weeks of continuous data recorded during 2000 Tottori earthquakes in Japan, we were able to detect and locate two times more earthquakes using only a portion (less than 1/3) of seismic stations. Our model picks P and S phases with precision close to manual picks by human analysts; however, its high efficiency and higher sensitivity can result in detecting and characterizing more and smaller events.

CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detection.

Earthquake signal detection is at the core of observational seismology. A good detection algorithm should be sensitive to small and weak events with a variety of waveform shapes, robust to background noise and non-earthquake signals, and efficient for processing large data volumes. Here, we introduce the Cnn-Rnn Earthquake Detector (CRED), a detector based on deep neural networks. CRED uses a combination of convolutional layers and bi-directional long-short-term memory units in a residual structure. It learns the time-frequency characteristics of the dominant phases in an earthquake signal from three component data recorded on individual stations. We train the network using 500,000 seismograms (250k associated with tectonic earthquakes and 250k identified as noise) recorded in Northern California. The robustness of the trained model with respect to the noise level and non-earthquake signals is shown by applying it to a set of semi-synthetic signals. We also apply the model to one month of continuous data recorded at Central Arkansas to demonstrate its efficiency, generalization, and sensitivity. Our model is able to detect more than 800 microearthquakes as small as -1.3 ML induced during hydraulic fracturing far away than the training region. We compare the performance of the model with the STA/LTA, template matching, and FAST algorithms. Our results indicate an efficient and reliable performance of CRED. This framework holds great promise for lowering the detection threshold while minimizing false positive detection rates.

Lateral Variation of Crustal Lg Attenuation in Eastern North America.

We perform Q Lg tomography for the northeastern part of North America. Vertical broadband seismograms of 473 crustal earthquakes recorded by 302 stations are processed to extract the Lg amplitude spectra. Tomographic inversions are independently conducted at 58 discrete frequencies distributed evenly in log space between 0.1 and 20.0 Hz. This relatively large dataset with good ray coverage allows us to image lateral variation of the crustal attenuation over the region. Obtained Q Lg maps at broadband and individual frequencies provide new insights into the crustal attenuation of the region and its relationship to geological structures and past tectonic activity in the area. The Q Lg shows more uniform values over the older, colder, and drier Canadian Shield, in contrast to higher variations in the younger margins. Results confirm the correlation of large-scale variations with crustal geological features in the area. Existence of low-velocity anomalies, thick sediments, volcanic rocks, and thin oceanic crust are potential sources of observed anomalies. The mean Q values are inversely correlated with average heat flow/generation for main geological provinces.