Classification of Local Seismic Events in the Utah Region: A Comparison of Amplitude Ratio Methods with a Spectrogram‐Based Machine Learning Approach

Abstract

The capability to discriminate low‐magnitude earthquakes from low‐yield anthropogenic sources, both detectable only at local distances, is of increasing interest to the event monitoring community. We used a dataset of seismic events in Utah recorded during a 14‐day period (1–14 January 2011) by the University of Utah Seismic Stations network to perform a comparative study of event classification at local scale using amplitude ratio (AR) methods and a machine learning (ML) approach. The event catalog consists of 7377 events with magnitudes MC ranging from −2 and lower up to 5.8. Events were subdivided into six populations based on location and source type: tectonic earthquakes (TEs), mining‐induced events (MIEs), and mining blasts from four known mines (WMB, SMB, LMB, and CQB). The AR approach jointly exploits Pg‐to‐Sg phase ARs and Rg‐to‐Sg spectral ARs in multivariate quadratic discriminant functions and was able to classify 370 events with high signal quality from the three groups with sufficient size (TE, MIE, and SMB). For that subset of the events, the method achieved success rates between about 80% and 90%. The ML approach used trained convolutional neural network (CNN) models to classify the populations. The CNN approach was able to classify the subset of events with accuracies between about 91% and 98%. Because the neural network approach does not have a minimum signal quality requirement, we applied it to the entire event catalog, including the abundant extremely low-magnitude events, and achieved accuracies of about 94%–100%. We compare the AR and ML methodologies using a broad set of criteria and conclude that a major advantage to ML methods is their robustness to low signal‐to‐noise ratio data, allowing them to classify significantly smaller events.

Microseismic Event Classification With Time-, Frequency-, and Wavelet-Domain Convolutional Neural Networks

“…A CNN is proposed in [11] to classify seismic events into 3 categories -tectonic earthquakes, mining-induced events, and mining blasts, based on 90sec long spectrograms as input. The model consists of 4 2-D convolutional and a 3-node softmax activated dense layer.…”

“…In contrast to traditional pipeline-based approaches, e.g., [4], [5], [6], [8], [9], deep learning provides an integrated approach to detection, feature representation and classification, with competitive performance under the assumption that a good representative dataset is available for training. Though there have been many attempts to use various deep learning architectures for seismic signal detection and classification (e.g., [10], [11], [12], [13], [14], [15]), classification of microseismic endogenous landslide events based on deep learning is rarely studied. Moreover, transferability of deep learning classification models to different monitoring network geometries is rarely discussed.…”

Combining Deep Learning With Physics Based Features in Explosion‐Earthquake Discrimination

“…There have also been several studies using recently developed deep learning based approaches to distinguish explosions from natural earthquakes (Kim et al., 2020; Kong et al., 2021; Linville et al., 2019; Magana‐Zook & Ruppert, 2017; Tibi et al., 2019). Linville et al.…”

“…There have also been several studies using recently developed deep learning based approaches to distinguish explosions from natural earthquakes (Kim et al, 2020;Kong et al, 2021;Linville et al, 2019;Magana-Zook & Ruppert, 2017;Tibi et al, 2019). Linville et al (2019) used convolutional and recurrent neural networks with spectrograms from seismic sensors as the input to classify explosions and tectonic sources at local distances, achieving 99% accuracy in terms of the source type discrimination.…”

Event‐Based Training in Label‐Limited Regimes

“…Although persistent seismic monitoring networks generate data‐rich event catalogs that enable the development of deep neural network (DNN) models capable of making accurate decisions about source attributes, they do so with a complex set of features only some of which may relate to the seismogenic processes that matter for predictive modeling tasks. Yet despite imperfect feature learning, performance on seismic processing tasks using stable network geometries can be superior to traditional methods (Linville et al., 2019; Ross et al., 2019; Tibi et al., 2019) and provide capabilities that scale as data volumes increase (Nguyen et al., 2019). Therefore, even when models generalize poorly to new regions, they can add consequential value to the specific event processing pipelines they were developed for.…”