Unsupervised Deep Clustering of Seismic Data: Monitoring the Ross Ice Shelf, Antarctica.

Advances in machine learning (ML) techniques and computational capacity have yielded state‐of‐the‐art methodologies for processing, sorting, and analyzing large seismic data sets. In this study, we consider an application of ML for automatically identifying dominant types of impulsive seismicity contained in observations from a 34‐station broadband seismic array deployed on the Ross Ice Shelf (RIS), Antarctica from 2014 to 2017. The RIS seismic data contain signals and noise generated by many glaciological processes that are useful for monitoring the integrity and dynamics of ice shelves. Deep clustering was employed to efficiently investigate these signals. Deep clustering automatically groups signals into hypothetical classes without the need for manual labeling, allowing for the comparison of their signal characteristics and spatial and temporal distribution with potential source mechanisms. The method uses spectrograms as input and encodes their salient features into a lower‐dimensional latent representation using an autoencoder, a type of deep neural network. For comparison, two clustering methods are applied to the latent data: a Gaussian mixture model (GMM) and deep embedded clustering (DEC). Eight classes of dominant seismic signals were identified and compared with environmental data such as temperature, wind speed, tides, and sea ice concentration. The greatest seismicity levels occurred at the RIS front during the 2016 El Niño summer, and near grounding zones near the front throughout the deployment. We demonstrate the spatial and temporal association of certain classes of seismicity with seasonal changes at the RIS front, and with tidally driven seismicity at Roosevelt Island. Plain Language Summary: We demonstrate the ability of a machine learning technique called deep clustering to automatically identify different types of seismic signals. A neural network encodes spectrograms into simplified representations. Application of a clustering algorithm separates the representations into distinct clusters of signal types. The deep clustering technique was applied to seismic data recorded by an extensive array of broadband seismometers deployed on the Ross Ice Shelf (RIS), Antarctica from 2014 to 2017. In addition to knowing when and where the RIS signals are detected, clustering enables users to determine the signal characteristics. Paired with environmental data, deep clustering can be used to identify whether certain environmental factors are associated with particular classes of seismicity. Key Points: Deep clustering identified classes of seismic signals with similar spectral and temporal featuresDeep clustering can be adapted to various kinds of data sets, enabling rapid exploration of "big data" in seismologyPaired with environmental data, deep clustering could provide insights into the causes of seismicity [ABSTRACT FROM AUTHOR]