12 Jul 2022
12 Jul 2022
Status: this preprint is open for discussion.

Machine learning prediction of the mass and the velocity of controlled single-block rockfalls from the seismic waves they generate

Clément Hibert1, François Noël2,3, David Toe5, Miloud Talib1, Mathilde Desrues1, Emmanuel Wyser2, Ombeline Brenguier6, Franck Bourrier4, Renaud Toussaint1,7, Jean-Philippe Malet1, and Michel Jaboyedoff2 Clément Hibert et al.
  • 1Institut Terre et Environnement de Strasbourg / ITES, CNRS & University of Strasbourg F-67084 Strasbourg, France
  • 2Institut des Sciences de la Terre / ISTE, University of Lausanne, Géopolis, CH-1015 Lausanne, Switzerland
  • 3Geological Survey of Norway, NO-7491 Trondheim, Norway
  • 4Université Grenoble Alpes, INRAE, ETNA, 38000 Grenoble, France
  • 5Université Grenoble Alpes, INRAE, LESSEM, 38000 Grenoble, France
  • 6Société Alpine de Géotechnique / SAGE, FR-38160 Gières, France
  • 7SFF Porelab, The Njord Centre, Department of Physics, University of Oslo, P. O. Box 1048, Blindern, N-0316 Oslo, Norway

Abstract. Understanding the dynamics of slope instabilities is critical to mitigate the associated hazards but their direct observation is often difficult due to their remote locations and their spontaneous nature. Seismology allows to get unique information on these events, including on their dynamics. However, the link between the properties of these events (mass and kinematics) and the seismic signals generated are still poorly understood. we conducted a controlled rockfall experiment in the Riou-Bourdoux torrent (South French Alps) to try to better decipher those links. We deployed a dense seismic network and inferred the dynamics of the block from the reconstruction of the 3D trajectory from terrestrial and airborne high-resolution stereo-photogrammetry. We propose a new approach based on machine learning to predict the mass and the velocity of each block. Our results show that we can predict those quantities with average errors of approximately 10 % for the velocity and 25 % for the mass. These accuracies are as good as or better than those obtained by other approaches, but our approach has the advantage of not requiring to localize the source and an a priori knowledge of the environment, nor of making a strong assumption on the seismic wave attenuation model. Finally, the machine learning approach allows us to explore more widely the correlations between the features of the seismic signal generated by the rockfalls and their physical properties, and might eventually lead to better constrain the physical models in the future.

Clément Hibert et al.

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Clément Hibert et al.

Clément Hibert et al.


Total article views: 425 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
247 169 9 425 7 6
  • HTML: 247
  • PDF: 169
  • XML: 9
  • Total: 425
  • BibTeX: 7
  • EndNote: 6
Views and downloads (calculated since 12 Jul 2022)
Cumulative views and downloads (calculated since 12 Jul 2022)

Viewed (geographical distribution)

Total article views: 367 (including HTML, PDF, and XML) Thereof 367 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 29 Nov 2022
Short summary
Natural disasters such as landslides and rock falls are mostly difficult to study because of the impossibility of making in situ measurements due to their destructive nature and spontaneous occurrence. Seismology is able to record the occurrence of such events from a distance and in real time. In this study, we show that using a machine learning approach, the mass and velocity of rockfalls can be estimated from the seismic signal they generate.