Articles | Volume 22, issue 4
Brief communication
04 Apr 2022
Brief communication |  | 04 Apr 2022

Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks

Pierpaolo Distefano, David J. Peres, Pietro Scandura, and Antonino Cancelliere

Data sets

The FraneItalia database M. Calvello and G. Pecoraro

Short summary
In the communication, we introduce the use of artificial neural networks (ANNs) for improving the performance of rainfall thresholds for 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. Adding peak rainfall intensity as input to the ANN improves performance even more. This further demonstrates the potentialities of the proposed machine learning approach.
Final-revised paper