Uncovering uncataloged low-frequency earthquake sources with deep learning

Documenting the interplay between slow deformation and the seismic ruptures is of great importance to better understand the physics of earthquakes nucleation. However, slow deformation is often difficult to detect and characterize. The most pervasive seismic markers of slow slip are low-frequency earthquakes (LFEs) that allow resolving deformations with minute-scale resolution. Detecting LFEs is hard, due to their emergent onsets and low signal-to-noise ratios, usually requiring region-specific template matching approaches. These approaches suffer from low flexibility and might miss LFEs as they are constrained to sources identified a priori. Here, we develop a deep learning-based workflow for LFE detection, modeled after a classical earthquake detection workflow with phase picking, phase association, and location. Across three regions with known LFE activity, we detect LFEs from both previously cataloged sources and newly identified sources. Furthermore, we show that the approach is transferable across regions, suggesting that it will enable systematic studies of LFEs in regions without known LFE activity. Zoom link: https://u-paris.zoom.us/j/84631356249?pwd=aCtvMVNWb0NIMkNBYmYyeXJMTlA5QT09