← Back to Gallery

Session: Filling the Data Gap: Ocean-bottom Sensing with Fiber-optic Cables [Poster]

Type: Poster

Date: 10/9/2024

Time: 07:00 AM

Room: Stanley Park Ballroom

Denoising Offshore Distributed Acoustic Sensing Using Masked Auto-encoders to Enhance Earthquake Detection

Offshore Distributed Acoustic Sensing (DAS) has emerged as a powerful technology for seismic monitoring, expanding the capacities of cable networks and coastal seismic networks to monitor offshore seismicity. However, DAS data often combine signals unfamiliar to seismologists, including new types of instrumental noise, fiber cable coupling issues, and ocean signals that overprint those from tectonic sources, all of which hinder seismological research. We develop a self-supervised deep learning algorithm, a Masked Auto-Encoder (MAE), to denoise DAS data for seismological purposes. The model is trained on randomly masked DAS channel recordings of local earthquakes in the Cook Inlet, offshore Alaska. To demonstrate the benefits of denoising for seismological research, we conduct the most fundamental steps to any earthquake catalog building: seismic phase picking, signal-to-noise ratio estimates, and event association. We leverage the generalizability of ensemble deep learning models with cross-correlation to predict phase picks with sufficient precision for post-processing (e.g., earthquake location). The signal-to-noise ratio (SNR) of the denoised testing DAS data increased by 2. The MAE denoised DAS data allows manyfold more S picks than the original noisy data for smaller regional earthquakes. The results demonstrate that our self-supervised MAE holds significant potential for enhancing seismic monitoring with rapid earthquake characterization.

Presenting Author: Qibin

Additional Authors