loading page

Machine Learning improves warning systems of debris flows
  • +3
  • Małgorzata Chmiel,
  • Fabian Walter,
  • Michaela Wenner,
  • Zhen Zhang,
  • McArdell Brian W.,
  • Clément Hibert
Małgorzata Chmiel
Laboratory of Hydraulics, Hydrology and Glaciology, ETH Zürich

Corresponding Author:chmielm@ee.ethz.ch

Author Profile
Fabian Walter
ETH Zürich
Author Profile
Michaela Wenner
ETH Zürich
Author Profile
Zhen Zhang
Institute of Mountain Hazards and Environment, Chinese Academy of Sciences
Author Profile
McArdell Brian W.
Swiss Federal Institute for Forest, Snow and Landscape Research WSL
Author Profile
Clément Hibert
Institut De Physique Du Globe De Strasbourg
Author Profile


Automatic identification of debris flow signals in continuous seismic records remains a challenge. To tackle this problem we use a machine learning approach, which can be applied to continuous real-time data streams. We show that a machine learning model based on the random forest algorithm recognizes different stages of debris flow formation and propagation at the Illgraben torrent, Switzerland, with an accuracy exceeding 90%. In contrast to typical debris flow detection requiring instrumentation installed directly in the torrent, our approach provides a significant gain in warning times of tens of minutes to hours. For real-time data streams from 2020, our detector raises alarms for all 8 independently confirmed Illgraben events and gives no false alarms. We suggest that our seismic machine-learning detector is a critical step towards the next generation of debris-flow warning, which increases warning times using both simpler and cheaper instrumentation compared to existing operational systems.