Continuous seismograms contain a wealth of information with a large variety of signals with different origin. Identifying these signals is a crucial step in understanding physical geological objects. We propose a strategy to identify classes of signals in continuous single‐station seismograms in an unsupervised fashion. Our strategy relies on extracting meaningful waveform features based on a deep scattering network combined with an independent component analysis. Based on the extracted features, agglomerative clustering then groups these waveforms in a hierarchical fashion and reveals the process of clustering in a dendrogram. We use the dendrogram to explore the seismic data and identify different classes of signals. To test our strategy, we investigate a two‐day‐long seismogram collected in the vicinity of the North Anatolian Fault, Turkey. We analyze the automatically inferred clusters' occurrence rate, spectral characteristics, cluster size, and waveform and envelope characteristics. At a low level in the cluster hierarchy, we obtain three clusters related to anthropogenic and ambient seismic noise and one cluster related to earthquake activity. At a high level in the cluster hierarchy, we identify a seismic burst that includes around 200 events with similar waveforms and high‐frequent signals with correlating envelopes and an anthropogenic origin. The application shows that the cluster hierarchy helps to identify particular families of signals and to extract subclusters for further analysis. This is valuable when certain types of signals, such as earthquakes, are under‐represented in the data. The proposed method may also successfully discover new types of signals since it is entirely data‐driven.

No abstract

In December 2018, the National Aeronautics and Space Administration (NASA) Interior exploration using Seismic Investigations, Geodesy and Heat Transport (InSight) mission deployed a seismometer on the surface of Mars. In preparation for the data analysis, in July 2017, the marsquake service initiated a blind test in which participants were asked to detect and characterize seismicity embedded in a one Earth year long synthetic data set of continuous waveforms. Synthetic data were computed for a single station, mimicking the streams that will be available from InSight as well as the expected tectonic and impact seismicity, and noise conditions on Mars (Clinton et al., 2017). In total, 84 teams from 20 countries registered for the blind test and 11 of them submitted their results in early 2018. The collection of documentations, methods, ideas, and codes submitted by the participants exceeds 100 pages. The teams proposed well established as well as novel methods to tackle the challenging target of building a global seismicity catalog using a single station. This article summarizes the performance of the teams and highlights the most successful contributions.