Preprints
https://doi.org/10.5194/egusphere-2022-950
https://doi.org/10.5194/egusphere-2022-950
 
04 Oct 2022
04 Oct 2022
Status: this preprint is open for discussion.

Machine learning nowcasting of the Vögelsberg deep-seated landslide: why predicting slow deformation is not so easy

Adriaan L. van Natijne1, Thom A. Bogaard2, Thomas Zieher3, Jan Pfeiffer3, and Roderik C. Lindenbergh1 Adriaan L. van Natijne et al.
  • 1Department of Geoscience & Remote Sensing, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands
  • 2Department of Water Management, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands
  • 3Institute for Interdisciplinary Mountain Research, Austrian Academy of Sciences, Innrain 25, 6020 Innsbruck, Austria

Abstract. Landslides are one of the major weather related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope processes is required. Landslide modelling is typically based on data-rich geomechanical models. Recently, machine learning has shown promising results in modelling a variety of processes. Furthermore, slope conditions are now also monitored from space, in wide-area repeat surveys from satellites. In the present study we tested if use of machine learning, combined with readily-available remote sensing data, allows us to build a deformation nowcasting model. A successful landslide deformation nowcast, based on remote sensing data and machine learning, would demonstrate effective understanding of the slope processes, even in the absence of physical modelling. We tested our methodology on the Vögelsberg, a deep-seated landslide near Innsbruck, Austria. Our results show that the formulation of such machine learning system is not as straightforward as often hoped for. Primary issue is the freedom of the model compared to the number of acceleration events in the time series available for training, as well as inherent limitations of the standard quality metrics. Satellite remote sensing has the potential to provide longer time series, over wide areas. However, although longer time series of deformation and slope conditions are clearly beneficial for machine learning based analyses, the present study shows the importance of the training data quality but also that this technique is mostly applicable to the well-monitored, more dynamic deforming landslides.

Adriaan L. van Natijne et al.

Status: open (until 28 Dec 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-950', Katy Burrows, 20 Oct 2022 reply

Adriaan L. van Natijne et al.

Adriaan L. van Natijne et al.

Viewed

Total article views: 296 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
210 80 6 296 3 2
  • HTML: 210
  • PDF: 80
  • XML: 6
  • Total: 296
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 04 Oct 2022)
Cumulative views and downloads (calculated since 04 Oct 2022)

Viewed (geographical distribution)

Total article views: 294 (including HTML, PDF, and XML) Thereof 294 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2022
Download
Short summary
Landslides are one of the major weather related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope is required. We tested if use of machine learning, combined with satellite remote sensing data, would allow us to forecast deformation. Our results on the Vögelsberg landslide, a deep-seated landslide near Innsbruck, Austria, show that the formulation of such machine learning system is not as straightforward as often hoped for.