Preprints
https://doi.org/10.5194/nhess-2021-206
https://doi.org/10.5194/nhess-2021-206

  12 Jul 2021

12 Jul 2021

Review status: this preprint is currently under review for the journal NHESS.

Brief communication: Rainfall thresholds based on Artificial neural networks can improve landslide early warning

Pierpaolo Distefano, David J. Peres, Pietro Scandura, and Antonino Cancelliere Pierpaolo Distefano et al.
  • Department of Civil Engineering and Architecture, University of Catania, Catania, 95123, Italy

Abstract. In this communication we show how the use of artificial neural networks (ANNs) can improve the performance of the rainfall thresholds for landslide early warning. Results for Sicily (Italy), show how performance of a traditional rainfall event duration and depth power law threshold, yielding a true skill statistic (TSS) of 0.50, can be improved by ANNs (TSS = 0.59). Then we show how ANNs allow to easily add other variables, like peak rainfall intensity, with a further performance improvement (TSS = 0.64). This may stimulate more research on the use of this powerful tool for deriving landslide early warning thresholds.

Pierpaolo Distefano et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2021-206', Anonymous Referee #1, 16 Jul 2021
    • AC1: 'Reply on RC1', David J. Peres, 05 Oct 2021
  • RC2: 'Comment on nhess-2021-206', Anonymous Referee #2, 12 Aug 2021
    • AC2: 'Reply on RC2', David J. Peres, 05 Oct 2021

Pierpaolo Distefano et al.

Pierpaolo Distefano et al.

Viewed

Total article views: 404 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
276 117 11 404 6 5
  • HTML: 276
  • PDF: 117
  • XML: 11
  • Total: 404
  • BibTeX: 6
  • EndNote: 5
Views and downloads (calculated since 12 Jul 2021)
Cumulative views and downloads (calculated since 12 Jul 2021)

Viewed (geographical distribution)

Total article views: 374 (including HTML, PDF, and XML) Thereof 374 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 16 Oct 2021
Download
Short summary
In this communication we show how the use of artificial neural networks (ANNs) can improve the performance of the rainfall thresholds for territorial landslide early warning. Results show how ANNs using rainfall event duration and mean intensity perform significantly better than a classical power-law based on the same variables. Including peak rainfall intensity as input to the ANN further improves performance, further demonstrating the potentialities of the proposed machine learning approach.
Altmetrics