Journal cover Journal topic
Natural Hazards and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

IF value: 3.102
IF3.102
IF 5-year value: 3.284
IF 5-year
3.284
CiteScore value: 5.1
CiteScore
5.1
SNIP value: 1.37
SNIP1.37
IPP value: 3.21
IPP3.21
SJR value: 1.005
SJR1.005
Scimago H <br class='widget-line-break'>index value: 90
Scimago H
index
90
h5-index value: 42
h5-index42
Download
Short summary
In mountainous areas, mass movements such as rockfalls, rock avalanches, and debris flows constitute a risk to property and human life. In this study we use machine learning to automatically detect and classify slope failure events using ground vibrations. We show that a near-real-time classification of seismogenic slope failures is feasible. Our approach enables us to detect the occurrence of rare events of high interest in a large data set of more than a million windowed seismic signals.
Altmetrics
Preprints
https://doi.org/10.5194/nhess-2020-200
https://doi.org/10.5194/nhess-2020-200

  08 Jul 2020

08 Jul 2020

Review status: a revised version of this preprint was accepted for the journal NHESS and is expected to appear here in due course.

Near Real-Time Automated Classification of Seismic Signals of Slope Failures with Continuous Random Forests

Michaela Wenner1,2, Clément Hibert3, Lorenz Meier4, and Fabian Walter1 Michaela Wenner et al.
  • 1Laboratory of Hydraulics, Hydrology and Glaciology (VAW), ETH Zurich, Zurich, Switzerland
  • 2Swiss Federal Institute for Forest, Snow and Landscape Research, Birmensdorf, Switzerland
  • 3Université de Strasbourg, CNRS, EOST/IPGS UMR 7516, F-67000 Strasbourg, France
  • 4Geopraevent Ltd., Zurich, Switzerland

Abstract. In mountainous areas, mass movements such as rockfalls, rock avalanches, and debris flows constitute a risk to prop- erty and human life. Seismology has evolved into a standard tool to study temporal and spatial variability of mass movements in recent years. Increasing data volumes and the demand for near real-time monitoring call for automated techniques to detect and classify seismic signals generated by such events. Ideally, a large-aperture seismic array recording a significant number of events is available for such applications. This is, however, rarely the case, as a result of cost and time constraints. For most sites, the number of previously recorded slope failures is low, which impedes a reliable application of classification algorithms. Here, we use supervised random forest to classify windowed seismic data on a continuous data stream of a small seismic array, that was installed as a post-event intervention measure after a major rock avalanche. The presented method aims to facilitate data evaluation for stakeholders to detect an increase in slope activity in a near real-time manner. We define three different classes: Noise, slope failures, and earthquakes. Due to the sparsity of slope failures, the training data set is highly imbalanced. We find that several standard techniques to handle such data sets do not increase prediction accuracy. However, a lowering of the prediction threshold for slope failures leads to a prediction accuracy of 80 % for slope failures, 90 % for earthquakes, and 99 % for noise. The classifier is then used to classify 176 days of seismic recordings in 2019 containing four slope failure events. In total, the model classifies eight events as slope failures, of which three are actual slope failures. The other events are very local to regional earthquakes with relatively large magnitudes. One slope failure that has been reported by hikers is not classified as an event. This can be attributed to the small volume of the slope failure and thus low signal to noise ratio. We conclude that the method is suitable for continuous near real-time seismic monitoring.

Michaela Wenner et al.

 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Michaela Wenner et al.

Michaela Wenner et al.

Viewed

Total article views: 385 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
250 121 14 385 18 19
  • HTML: 250
  • PDF: 121
  • XML: 14
  • Total: 385
  • BibTeX: 18
  • EndNote: 19
Views and downloads (calculated since 08 Jul 2020)
Cumulative views and downloads (calculated since 08 Jul 2020)

Viewed (geographical distribution)

Total article views: 469 (including HTML, PDF, and XML) Thereof 467 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 Jan 2021
Publications Copernicus
Download
Short summary
In mountainous areas, mass movements such as rockfalls, rock avalanches, and debris flows constitute a risk to property and human life. In this study we use machine learning to automatically detect and classify slope failure events using ground vibrations. We show that a near-real-time classification of seismogenic slope failures is feasible. Our approach enables us to detect the occurrence of rare events of high interest in a large data set of more than a million windowed seismic signals.
Citation
Altmetrics