Speech-recognition in landslide predictive modelling: A case for a next generation early warning system

Zhice Fang, Hakan Tanyas, Tolga Gorum, Ashok Dahal, Yi Wang, Luigi Lombardo*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Traditional landslide early warnings are based on the notion that intensity-duration relations can be approximated to single precipitation values cumulated over fixed time windows. Here, we take on a similar task being inspired by modeling architectures typical of speech-recognition tasks. We aim at classifying the Turkish landscape into 5 km grids assigned with dynamic landslide susceptibility estimates. We collected all available national information on precipitation-induced landslide occurrences. This information is passed to a Long Short-Term Memory equipped with the whole rainfall time series, obtained from daily CHIRPS data. We test this model: 1) by randomizing the presence/absence data to represent the slope instability over Turkey and over 13 years under consideration (2008–2020) and 2) by assessing the effect of different time windows used to pass the rainfall signal to the neural network. Results show that the inclusion of the full precipitation signal rather than its scalar approximation leads to a substantial increase in prediction power (approximately 20%). This may potentially pave the road for a new generation of speech-recognition-based landslide early warning systems.

Original languageEnglish
Article number105833
JournalEnvironmental Modelling and Software
Volume170
DOIs
Publication statusPublished - Dec 2023

Bibliographical note

Publisher Copyright:
© 2023 The Authors

Funding

This work was supported by the Joint Funds of the National Natural Science Foundation of China ( U21A2013 ) and the Fundamental Research Funds for National Universities , China University of Geosciences (Wuhan) . Initial idea proposed by Ashok Dahal. Experimental design developed by Zhice Fang, Luigi Lombardo and Hakan Tanyas. The same authors have prepared scientific illustrations and written the manuscript. Zhice Fang has also worked on the implementation. Tolga Gorum provided the data. Yi Wang secured the above mentioned funds. The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Luigi Lombardo reports financial support was provided by National Natural Science Foundation of China.This work was supported by the Joint Funds of the National Natural Science Foundation of China (U21A2013) and the Fundamental Research Funds for National Universities, China University of Geosciences (Wuhan). Initial idea proposed by Ashok Dahal. Experimental design developed by Zhice Fang, Luigi Lombardo and Hakan Tanyas. The same authors have prepared scientific illustrations and written the manuscript. Zhice Fang has also worked on the implementation. Tolga Gorum provided the data. Yi Wang secured the above mentioned funds.

FundersFunder number
Ashok Dahal
Fundamental Research Funds for National Universities
National Natural Science Foundation of ChinaU21A2013
China University of Geosciences, Wuhan

    Keywords

    • Early warning system
    • Landslide prediction
    • Precipitation
    • Speech recognition
    • Time series

    Fingerprint

    Dive into the research topics of 'Speech-recognition in landslide predictive modelling: A case for a next generation early warning system'. Together they form a unique fingerprint.

    Cite this