← 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

Wavefield Reconstruction of Distributed Acoustic Sensing: Compression, Wavefield Separation, and Edge Computing

Distributed Acoustic Sensing (DAS) is a new seismic observation method. DAS dramatically expands the ability of dense seismic observation and has been used for ocean observation, sub-surface imaging, volcano monitoring, and earthquake characterization. While the high rate of data benefits research analysis, they are problematic for data transmission and storage and limit the real-time or large-scale application of DAS. Data compression algorithms accelerate the transmission by transforming the raw data into smaller sizes, however, at the cost of more computing time and data distortion.

In this study, we explore wavefield reconstruction using Deep Learning (DL) methods for wavefield compression, reconstruction, and separation. We test SHallow REcurrent Decoder (SHRED) that generalizes over space and time for a single optical fiber with 20% decimated channels for the reconstruction. Despite good performance in reconstructing long-wavelength features, our model does not reconstruct transient earthquake wavefields at shorter wavelengths, limiting its usability for seismic data transmission. Nevertheless, we leverage wavefield reconstruction of ocean waves to separate them from the seismic wavefield and improve seismological use cases for earthquake detection and Earth imaging. At last, we evaluate the model accuracy, adaptivity, computing expense and generalizability on the Cook Inlet DAS experiment.

Presenting Author: Yiyu

Additional Authors