← Back to Gallery

Session: Exploring the Frontier of Environmental Processes using Fiber-optic Sensing [Poster]

Type: Poster

Date: 10/9/2024

Time: 07:00 AM

Room: Stanley Park Ballroom

Automatic Monitoring of Rock-Slope Failures Using Distributed Acoustic Sensing and Semi-Supervised Learning

Distributed Acoustic Sensing (DAS) represents a leap in seismic monitoring capabilities. Compared to traditional single-seismometer stations, DAS measures seismic strain at meter to sub-meter intervals along fiber-optic cables thus offering unprecedented temporal and spatial resolution. However, the effective use of the wealth of information provided by DAS for natural hazard and in particular mass movement monitoring remains a challenge.

We propose a semi-supervised neural network tailored to screen DAS data related to a major rock collapse on 15 June 2023 and precursory failures near Brienz, Eastern Switzerland. Besides DAS, our dataset from 16 May to 30 June 2023 includes Doppler radar data for ground-truth labeling. The proposed algorithm is capable of distinguishing between rock-slope failures and background noise, including road and train traffic, with a detection precision of over 90%. It identifies hundreds of precursory failures and shows sustained detection hours before and during the major collapse. Moreover, we have identified key performance dependencies: event size and signal-to-noise ratio (SNR). As a critical part of our algorithm operates in an unsupervised way we suggest that it is suitable for general monitoring of gravitational hazards.

The major collapse is characterized by strong low-frequency signals between 0.01 and 0.03 Hz across multiple channels of the cable's trajectory-parallel section. Most of this low-frequency energy arrives after the high-frequency signal. Our initial hypothesis is that the low-frequency signal relates to a bulk mass moving downslope. However, the Doppler radar does not fully capture this movement, possibly due to radar insensitivity immediately following the collapse. Further investigation will focus on force-history inversion to study the seismic source mechanisms during the major collapse.

Presenting Author: Jiahui

Additional Authors