Automatic Monitoring of Rock-Slope Failures Using Distributed Acoustic Sensing and Semi-Supervised Learning
Abstract
Effective use of the wealth of information provided by Distributed Acoustic Sensing (DAS) for mass movement monitoring remains a challenge. We propose a semi‐supervised neural network tailored to screen DAS data related to a series of rock collapses leading to a major failure of approximately 1.2 million on 15 June 2023 in Brienz, Eastern Switzerland. Besides DAS, the dataset from 16 May to 30 June 2023 includes Doppler radar data for partially 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 . It identifies hundreds of precursory failures and shows sustained detection hours before and during the major collapse. Event size and signal‐to‐noise ratio (SNR) are the key performance dependencies. As a critical part of our algorithm operates unsupervised, we suggest that it is suitable for general monitoring of natural hazards.
Related
- SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing
- Exploring the potential of distributed acoustic sensing for fish bioacoustics
- Characterizing the Modes of Earth’s Free Oscillations via Submarine Distributed Acoustic Sensing (DAS)
- Evaluation of Distributed Acoustic Sensing (DAS) Systems with Polarization Diversity for Railway Infrastructure: Effects of Fiber Type and Installation Conditions on System Performance
- Bridge Vibrations as Persistent Seismic Sources for Time-lapse Imaging of River Corridors with Distributed Acoustic Sensing
BibTeX
@article{kang2026automatic,
title = {{Automatic Monitoring of Rock-Slope Failures Using Distributed Acoustic Sensing and Semi-Supervised Learning}},
author = {Jiahui Kang and Fabian Walter and Patrick Paitz and Johannes Aichele and Pascal Edme and Lorenz Meier and Andreas Fichtner},
journal = {Geophysical Research Letters},
year = {2026},
month = oct,
doi = {10.1029/2024gl110672},
url = {https://hal.science/hal-05789553v1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Automatic Monitoring of Rock-Slope Failures Using Distributed Acoustic Sensing and Semi-Supervised Learning
AU - Jiahui Kang
AU - Fabian Walter
AU - Patrick Paitz
AU - Johannes Aichele
AU - Pascal Edme
AU - Lorenz Meier
AU - Andreas Fichtner
PY - 2026
DA - 2026/10/09
JO - Geophysical Research Letters
DO - 10.1029/2024gl110672
UR - https://hal.science/hal-05789553v1
AB - Effective use of the wealth of information provided by Distributed Acoustic Sensing (DAS) for mass movement monitoring remains a challenge. We propose a semi‐supervised neural network tailored to screen DAS data related to a series of rock collapses leading to a major failure of approximately 1.2 million on 15 June 2023 in Brienz, Eastern Switzerland. Besides DAS, the dataset from 16 May to 30 June 2023 includes Doppler radar data for partially 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 . It identifies hundreds of precursory failures and shows sustained detection hours before and during the major collapse. Event size and signal‐to‐noise ratio (SNR) are the key performance dependencies. As a critical part of our algorithm operates unsupervised, we suggest that it is suitable for general monitoring of natural hazards.
SN - 0094-8276
SN - 1944-8007
ER -