Coastal Flood Vulnerability Mapping using Remote Sensing, GIS and Machine Learning Techniques: A Case Study of Cheyyur Taluk, Chengalpattu District, Tamil Nadu, India
Disaster Advances · 03.06.2026 · 7 (19) · 22
DOI: 10.25303/197da22031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Disaster Advances, online erschienen am 03.06.2026. Verfasst von Jayachandran Mani und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Coastal flooding is a recurring natural hazard that poses serious threats to human settlements, infrastructure and ecosystems in low-lying coastal regions. The eastern coast of India is particularly vulnerable due to intense monsoonal rainfall, cyclonic activity, gentle coastal slopes and rapid land-use changes. In this study, an integrated Remote Sensing (RS), Geographic Information System (GIS), Analytical Hierarchy Process (AHP) and Machine Learning (ML) approach was employed to assess coastal flood hazard and vulnerability in Cheyyur taluk, Chengalpattu district, Tamil Nadu, covering an area of 615.82 km². Multi-source geospatial datasets, including Sentinel-2 imagery and SRTM DEM, were used to derive topographic, hydrological, geomorphological, landuse and spectral flood-conditioning parameters. Landuse/land cover was mapped using a machine learning–based Random Forest classifier, while AHP was applied to assign relative weights to twenty-two flood-influencing factors and generate a composite flood vulnerability index. The resulting flood hazard map classified the study area into very low, low, moderate, high and very high vulnerability zones. The results revealed that Kottaikadu, Cheyyur, Swarnabhoomi, Kuvathur and Melmaruvathur fall under high to very high flood vulnerability whereas Vennangupattu, Pondur and Kayapakkam exhibit moderate vulnerability and Pavunjur and Chithamur are characterized by low to very low flood risk. The spatial distribution of flood-prone areas closely corresponds with low elevation, proximity to drainage networks and the coastline, floodplain geomorphology and moisture-rich land surface conditions. The study highlights the effectiveness of the integrated RS–GIS–AHP–ML framework for coastal flood hazard assessment and provides critical inputs for flood risk mitigation, landuse planning and sustainable coastal zone management in vulnerable coastal regions.
Zitieren
APA
Mani, J., Rahim, A. I. A., Moorthy, P., & Chokkalingam, L. (2026). Coastal Flood Vulnerability Mapping using Remote Sensing, GIS and Machine Learning Techniques: A Case Study of Cheyyur Taluk, Chengalpattu District, Tamil Nadu, India. Disaster Advances, 7(19), 22. https://doi.org/10.25303/197da22031
Vancouver
Mani J, Rahim AIA, Moorthy P, Chokkalingam L. Coastal Flood Vulnerability Mapping using Remote Sensing, GIS and Machine Learning Techniques: A Case Study of Cheyyur Taluk, Chengalpattu District, Tamil Nadu, India. Disaster Advances. 2026;7(19):22. doi:10.25303/197da22031
BibTeX
@article{Mani2026,
author = {Mani, Jayachandran and Rahim, Ahamed Ibrahim Abdul and Moorthy, Prabhakaran and Chokkalingam, Lakshumanan},
title = {Coastal Flood Vulnerability Mapping using Remote Sensing, GIS and Machine Learning Techniques: A Case Study of Cheyyur Taluk, Chengalpattu District, Tamil Nadu, India},
journal = {Disaster Advances},
year = {2026},
volume = {7},
number = {19},
pages = {22},
doi = {10.25303/197da22031}
}
EUVIMED