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

Fang Z., Tanyas H., Görüm T., Dahal A., Wang Y., Lombardo L.

Environmental Modelling and Software, cilt.170, 2023 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 170
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1016/j.envsoft.2023.105833
  • Dergi Adı: Environmental Modelling and Software
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Applied Science & Technology Source, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Biotechnology Research Abstracts, CAB Abstracts, Communication Abstracts, Compendex, Computer & Applied Sciences, Environment Index, Geobase, Greenfile, INSPEC, Metadex, Pollution Abstracts, Public Affairs Index, Veterinary Science Database, Civil Engineering Abstracts
  • Anahtar Kelimeler: Early warning system, Landslide prediction, Precipitation, Speech recognition, Time series
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

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.