Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks
<p>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...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2022-04-01
|
Series: | Natural Hazards and Earth System Sciences |
Online Access: | https://nhess.copernicus.org/articles/22/1151/2022/nhess-22-1151-2022.pdf |
_version_ | 1811311541393293312 |
---|---|
author | P. Distefano D. J. Peres P. Scandura A. Cancelliere |
author_facet | P. Distefano D. J. Peres P. Scandura A. Cancelliere |
author_sort | P. Distefano |
collection | DOAJ |
description | <p>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 <span class="inline-formula">=</span> 0.59). Then we show how ANNs allow other variables to be easily added, like peak rainfall intensity, with a further performance
improvement (TSS <span class="inline-formula">=</span> 0.66). This may stimulate more research on the use of this powerful tool for deriving landslide early warning thresholds.</p> |
first_indexed | 2024-04-13T10:20:52Z |
format | Article |
id | doaj.art-974ee26a001e467f9ad4c2156d21c083 |
institution | Directory Open Access Journal |
issn | 1561-8633 1684-9981 |
language | English |
last_indexed | 2024-04-13T10:20:52Z |
publishDate | 2022-04-01 |
publisher | Copernicus Publications |
record_format | Article |
series | Natural Hazards and Earth System Sciences |
spelling | doaj.art-974ee26a001e467f9ad4c2156d21c0832022-12-22T02:50:31ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812022-04-01221151115710.5194/nhess-22-1151-2022Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networksP. DistefanoD. J. PeresP. ScanduraA. Cancelliere<p>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 <span class="inline-formula">=</span> 0.59). Then we show how ANNs allow other variables to be easily added, like peak rainfall intensity, with a further performance improvement (TSS <span class="inline-formula">=</span> 0.66). This may stimulate more research on the use of this powerful tool for deriving landslide early warning thresholds.</p>https://nhess.copernicus.org/articles/22/1151/2022/nhess-22-1151-2022.pdf |
spellingShingle | P. Distefano D. J. Peres P. Scandura A. Cancelliere Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks Natural Hazards and Earth System Sciences |
title | Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks |
title_full | Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks |
title_fullStr | Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks |
title_full_unstemmed | Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks |
title_short | Brief communication: Introducing rainfall thresholds for landslide triggering based on artificial neural networks |
title_sort | brief communication introducing rainfall thresholds for landslide triggering based on artificial neural networks |
url | https://nhess.copernicus.org/articles/22/1151/2022/nhess-22-1151-2022.pdf |
work_keys_str_mv | AT pdistefano briefcommunicationintroducingrainfallthresholdsforlandslidetriggeringbasedonartificialneuralnetworks AT djperes briefcommunicationintroducingrainfallthresholdsforlandslidetriggeringbasedonartificialneuralnetworks AT pscandura briefcommunicationintroducingrainfallthresholdsforlandslidetriggeringbasedonartificialneuralnetworks AT acancelliere briefcommunicationintroducingrainfallthresholdsforlandslidetriggeringbasedonartificialneuralnetworks |