Array-Based Convolutional Neural Networks for Automatic Detection and 4D Localization of Earthquakes in Hawai‘i

The growing amount of seismic data necessitates efficient and effective methods to monitor earthquakes. Current methods are computationally expensive, ineffective under noisy environments, or labor intensive. We leverage advances in machine learning to propose an improved solution, ArrayConvNet—a convolutional neural network that uses continuous array data from a seismic network to seamlessly detect and localize events, without the intermediate steps of phase detection, association, travel-time calculation, and inversion. When testing this methodology with events at Hawai‘i, we achieve 99.4% accuracy and predict hypocenter locations within a few kilometers of the U.S. Geological Survey catalog. We demonstrate that training with relocated earthquakes reduces localization errors significantly. We outline several ways to improve the model, including enhanced data augmentation and use of relocated offshore earthquakes recorded by ocean-bottom seismometers. Application to continuous records shows that our algorithm detects 690% as many earthquakes as the published catalog, and 125% as many events than the Hawaiian Volcano Observatory internal catalog. Because of the enhanced detection sensitivity, localization granularity, and minimal computation costs, our solution is valuable, particularly for real-time earthquake monitoring.

Supplemental Material: Periodic dike intrusions at Kīlauea volcano, Hawaiʻi

Supplemental information on regional terminology, methods, models, and analysis. The Hawaiian Volcano Observatory earthquake catalog can be downloaded from: https://www.usgs.gov/observatories/hawaiian-volcano-observatory/earthquakes/.<br>

Supplemental Material: Periodic dike intrusions at Kīlauea volcano, Hawaiʻi

Supplemental information on regional terminology, methods, models, and analysis. The Hawaiian Volcano Observatory earthquake catalog can be downloaded from: https://www.usgs.gov/observatories/hawaiian-volcano-observatory/earthquakes/.<br>

Hawaiian Volcano Observatory Searches for a New Home

Seismic activity during the eruption of Kīlauea damaged the Hawaiian Volcano Observatory beyond repair. Now officials are looking for a new site.

Long-Term Subsidence in Lava Fields at Piton de la Fournaise Volcano Measured by InSAR: New Insights for Interpretation of the Eastern Flank Motion

Long-term deformation often occurs in lava fields at volcanoes after flow emplacements. The investigation and interpretation of deformation in lava fields is one of the key factors for the assessment of volcanic hazards. As a typical Hawaiian volcano, Piton de la Fournaise volcano’s (La Réunion Island, France) main eruptive production is lava. Characteristics of the lava flows at Piton de la Fournaise, including the geometric parameters, location, and elevation, have been investigated by previous studies. However, no analysis focusing on the long-term post-emplacement deformation in its lava fields at a large spatial extent has yet been performed. One of the previous studies revealed that the post-emplacement lava subsidence played a role in the observed Eastern Flank motion by conducting a preliminary investigation. In this paper, an InSAR time series analysis is performed to characterize the long-term deformation in lava fields emplaced between 1998 and 2007 at Piton de la Fournaise, and to conduct an in-depth investigation over the influence of post-emplacement lava subsidence processes on the instability of the Eastern Flank. Results reveal an important regional difference in the subsidence behavior between the lava fields inside and outside of the Eastern Flank Area (EFA), which confirms that, in addition to the post-lava emplacement processes, other processes must have played a role in the observed subsidence in the EFA. The contribution of other processes is estimated to be up to ~78%. The spatial variation of the observed displacement in the EFA suggests that a set of active structures (like normal faults) could control a slip along a pre-existing structural discontinuity beneath the volcano flank. This study provides essential insights for the interpretation of the Eastern Flank motion of Piton de la Fournaise.