Aaron Wech | Geology Reports

USGS2025

A northeast-dipping zone of low frequency earthquakes at the southern edge of Cascadia subduction

Tectonic tremor monitoring occasionally detects events in an anomalous zone in southern Cascadia, 50–100 km west of the main tremor band, near the expected southern edge of the subducting Gorda slab at the Mendocino triple junction. To investigate the geometry and temporal behavior of this tremor, we examine its constituent low-frequency earthquakes (LFEs) by developing 27 stacked LFE waveform templates that we use to detect events from 2018 to 2024. We then relocate LFE sources together with regional seismicity. We find that LFE hypocenters form a northeast-dipping alignment at 22–29 km depth, extending eastward from a zone of micro-earthquakes, ∼15 km south of the southern edge of Gorda slab seismicity. These LFE families exhibit small bursts of activity every few days. Considering the strong world-wide association of tremor and LFEs with high slip-rate, plate-bounding faults, we hypothesize these LFEs may demark the southern edge of Cascadia subduction.

California↗

USGS2025

A generalized deep learning model to detect and classify volcano seismicity

Volcano seismicity is often detected and classified based on its spectral properties. However, the wide variety of volcano seismic signals and increasing amounts of data make accurate, consistent, and efficient detection and classification challenging. Machine learning (ML) has proven very effective at detecting and classifying tectonic seismicity, particularly using Convolutional Neural Networks (CNNs) and leveraging labeled datasets from regional seismic networks. Progress has been made applying ML to volcano seismicity, but efforts have typically been focused on a single volcano and are often hampered by the limited availability of training data. We build on the method of Tan et al. [2024] ( 10.1029/2024JB029194 ) to generalize a spectrogram-based CNN termed the VOlcano Infrasound and Seismic Spectrogram Neural Network ( VOISS-Net ) to detect and classify volcano seismicity at any volcano. We use a diverse training dataset of over 270,000 spectrograms from multiple volcanoes: Pavlof, Semisopochnoi, Tanaga, Takawangha, and Redoubt volcanoes\replaced (Alaska, USA); Mt. Etna (Italy); and Kīlauea, Hawai`i (USA). These volcanoes present a wide range of volcano seismic signals, source-receiver distances, and eruption styles. Our generalized VOISS-Net model achieves an accuracy of 87 % on the test set. We apply this model to continuous data from several volcanoes and eruptions included within and outside our training set, and find that multiple types of tremor, explosions, earthquakes, long-period events, and noise are successfully detected and classified. The model occasionally confuses transient signals such as earthquakes and explosions and misclassifies seismicity not included in the training dataset (e.g. teleseismic earthquakes). We envision the generalized VOISS-Net model to be applicable in both research and operational volcano monitoring settings.

Volcanica↗