Near-real-time automated classification of seismic signals of slope failures with continuous random forests

• Published in: Natural hazards and earth system sciences Vol. 21; no. 1; pp. 339 - 361
• Main Authors: Wenner, Michaela, Hibert, Clément, van Herwijnen, Alec, Meier, Lorenz, Walter, Fabian
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 27.01.2021; Copernicus Publ. / European Geosciences Union; Copernicus Publications
• Subjects: Accuracy; Algorithms; Analysis; Automation; Avalanches; Catastrophic failure analysis; Classification; Confusion; Data mining; Data transmission; Datasets; Debris flow; Decision making; Decision trees; Detection; Earthquakes; Failure; Failures; Information management; Landslides; Learning algorithms; Machine learning; Mass; Mountain regions; Mountainous areas; Predictions; Rain; Real time; Rock falls; Rocks; Rockslides; Sciences of the Universe; Seismic activity; Seismic data; Seismograms; Seismological data; Seismology; Signal classification; Signal monitoring; Signal to noise ratio; Slopes; Snow avalanches; Training; Switzerland

In mountainous areas, rockfalls, rock avalanches, and debris flows constitute a risk to human life and property. Seismology has proven a useful tool to monitor such mass movements, while increasing data volumes and availability of real-time data streams demand new solutions for automatic signal clas...