Continuous seismograms contain a wealth of information with a large variety of signals with different origins. Identifying these signals is a crucial step in understanding physical geological objects. We propose a strategy to identify classes of seismic 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 in- dependent 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 crisis that includes more than 200 repeating events and high-frequent signals with correlated 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.

Seismograms always result from mixing many sources and medium changes that are complex to disentangle, witnessing many physical phenomena within the Earth. With artificial intelligence (AI), we isolate the signature of surface freezing and thawing in continuous seismograms recorded in a noisy urban environment. We perform a hierarchical clustering of the seismograms and identify a pattern that correlates with ground frost periods. We further investigate the fingerprint of this pattern and use it to track the continuous medium change with high accuracy and resolution in time. Our method isolates the effect of the ground frost and describes how it affects the horizontal wavefield. Our findings show how AI-based strategies can help to identify and understand hidden patterns within seismic data caused either by medium or source changes.

We study how ground frost affects the ambient seismic wavefield recorded by a three-component broadband sensor. By applying machine learning algorithms on continuous seismic data, we can retrieve the seismic signature of the continuous freeze and thaw process at the surface of the ground. The retrieved signature reveals that the presence of ground frost imprints the amplitude of the ambient seismic wavefield, and the energy ratio between horizontal and vertical components (H/V). A regression model can even predict diurnal freeze and thaw patterns based on the seismic data. Thus, we assume that slight changes in the physical properties of the frozen surface, such as the thickness, alter the seismic wavefield. Models of the subsurface with different properties of the ground frost agree with the observations from the field. The penetration depth of the ground frost, the temperature of the frozen ground, and the presence of different modes in the wavefield determine how the seismic wavefield is changing. The findings of this study show the potential of a single seismic station for monitoring frozen bodies near the surface, such as permafrosts.