Advancing Coastal Flood Risk Prediction Utilizing a GeoAI Approach by Considering Mangroves as an Eco-DRR Strategy

Atmaja, Tri, Setiawati, Martiwi Diah, Kurisu, Kiyo and Fukushi, Kensuke, (2024). Advancing Coastal Flood Risk Prediction Utilizing a GeoAI Approach by Considering Mangroves as an Eco-DRR Strategy. Hydrology, 11(12), n/a-n/a

Document type:
Article
Collection:
UNU-IAS Journal Articles

Metadata
Documents
Links
Versions
Statistics
  • Attached Files (Some files may be inaccessible until you login with your UNU Collections credentials)
    Name Description MIMEType Size Downloads
    Atmaja_et_al._23_11_2024.pdf Atmaja_et_al._23_11_2024.pdf application/pdf 6.92MB
  • Sub-type Journal article
    Author Atmaja, Tri
    Setiawati, Martiwi Diah
    Kurisu, Kiyo
    Fukushi, Kensuke
    Title Advancing Coastal Flood Risk Prediction Utilizing a GeoAI Approach by Considering Mangroves as an Eco-DRR Strategy
    Appearing in Hydrology
    Volume 11
    Issue No. 12
    Publication Date 2024-11-23
    Place of Publication Basel
    Publisher MDPI
    Start page n/a
    End page n/a
    Language eng
    Abstract Traditional coastal flood risk prediction often overlooks critical geographic features, underscoring the need for accurate risk prediction in coastal cities to ensure resilience. This study enhances the prediction of coastal flood occurrence by utilizing the Geospatial Artificial Intelligence (GeoAI) approach. This approach employed models—random forest (RF), k-nearest neighbor (kNN), and artificial neural networks (ANN)—and compared them to the IPCC risk framework. This study used El Salvador as a demonstration case. The models incorporated seven input variables: extreme sea level, coastline proximity, elevation, slope, mangrove distance, population, and settlement type. With a recall score of 0.67 and precision of 0.86, the RF model outperformed the other models and the IPCC approach, which could avoid imbalanced datasets and standard scaler issues. The RF model improved the reliability of flood risk assessments by reducing false negatives. Based on the RF model output, scenario analysis predicted a significant increase in flood occurrences by 2100, mainly under RCP8.5 with SSP5. The study also highlights that the continuous mangrove along the coastline will reduce coastal flood occurrences. The GeoAI approach results suggest its potential for coastal flood risk management, emphasizing the need to integrate natural defenses, such as mangroves, for coastal resilience.
    Keyword Artificial Intelligence
    Coastal flood risk
    Coastal resilience
    Disaster risk management
    Mangrove forest
    Copyright Holder The Authors
    Copyright Year 2024
    Copyright type Creative commons
    ISSN 2306-5338
    DOI 10.3390/hydrology11120198
  • Versions
    Version Filter Type
  • Citation counts
    Google Scholar Search Google Scholar
    Access Statistics: 50 Abstract Views, 8 File Downloads  -  Detailed Statistics
    Created: Mon, 25 Nov 2024, 16:03:39 JST by Anne Lecroq on behalf of UNU IAS