Remote Sensing and Machine Learning-Driven Flood Inundation Mapping of September 2025 Ravi Watershed Using Sentinel-1 SAR
International Journal of Innovations in Science and Technology · 08.10.2025 · 2338
DOI: 10.33411/ijist/1582 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 08.10.2025. Verfasst von Bareera Bilal und 3 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Floods is among the most devastating natural hazards in South Asia. The September 2025 flood in the Ravi Basin was triggered by heavy monsoon rainfall and the release of water from cross-border dams. This study utilized Sentinel-1 SAR data, including both ascending and descending passes in VH polarization, to map flood inundation across the basin using a Random Forest classifier. Pre-flood and post-flood composites were prepared for April-May and 27 August to 5 September, respectively. The predictors feature includes VH_pre, VH_post, VH_diff, and VH_ratio. Terrain correction using the NASA DEM and landcover filtering with ESA WorldCover at 10m improved classification accuracy. Results showed that 1,885 km² of land was inundated, representing 5% of the total basin area. Approximately 260 settlements were impacted, including Dera Baba Nanak, Kartarpur, and the low-lying regions of Lahore. Croplands were the most affected class, with 1,610 km² flooded, followed by grasslands (90 km²) and sparse vegetation (62 km²). Built-up areas accounted for 0.7 km² of inundation, though the socio-economic impact was disproportionately high. Precipitation analysis from NOAA CPC confirmed rainfall clustering in the Sialkot and Narowal corridor. The peaks exceeding 800 mm/day cause this region as the epicenter of the flood. News reports corroborated satellite findings, noting that over 2.5 million displaced and more than 100 lives were lost. The study highlights how tributary floods involving the Ravi, Sutlej, and Chenab are emerging as severe hazards for Punjab. Findings underline the need for improved monitoring, resilient agricultural strategies, and disaster preparedness to mitigate future economic and food security risks.
Zitieren
APA
Bilal, B., Saleemi, R., Amer, A., & Gulzar, H. (2025). Remote Sensing and Machine Learning-Driven Flood Inundation Mapping of September 2025 Ravi Watershed Using Sentinel-1 SAR. International Journal of Innovations in Science and Technology, 2338. https://doi.org/10.33411/ijist/1582
Vancouver
Bilal B, Saleemi R, Amer A, Gulzar H. Remote Sensing and Machine Learning-Driven Flood Inundation Mapping of September 2025 Ravi Watershed Using Sentinel-1 SAR. International Journal of Innovations in Science and Technology. 2025:2338. doi:10.33411/ijist/1582
BibTeX
@article{Bilal2025,
author = {Bilal, Bareera and Saleemi, Rania and Amer, Areeba and Gulzar, Hamid},
title = {Remote Sensing and Machine Learning-Driven Flood Inundation Mapping of September 2025 Ravi Watershed Using Sentinel-1 SAR},
journal = {International Journal of Innovations in Science and Technology},
year = {2025},
pages = {2338},
doi = {10.33411/ijist/1582}
}
EUVIMED