.png){kind=icon}
Return
Inter-annual flood mapping using a cloud computing platform and multi-source spatial data
.png){kind=icon}
OA
AI
DOI：10.1080/10106049.2026.2684368.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Flooding is one of the devastating natural disasters globally, with developing areas vulnerable due to insufficient data availability. This study develops an inter-annual flood extent mapping framework using Google Earth Engine Platform and multi-source spatial datasets to assess flood patterns and evaluate land-use impacts over 2020–2024. Sentinel-1 SAR data were used for mapping flood extent through threshold-based change detection, while Sentinel-2 data with random forest algorithms enabled land use classification. Results indicate substantial inter-annual variations in flood extent, fluctuating between 30,823 ha (2024) and 488,070 ha (2021), showing strong correlation with regional rainfall patterns. Cropland areas experienced flooding of up to 39,363 ha in 2023, while built-up areas recorded approximately 80,711 ha of inundation in 2021. The derived rainfall thresholds provide foundations for early warning systems. This scalable methodology contributes to enhanced flood risk management and climate resilience, informing policy development for achieving sustainable development goals in flood-prone regions.
Keywords:
Climate resilience
disaster preparedness
flood risk management
insufficient data availability
machine Learning
Journal
IF:
3.5
Papers:
2.4K
Citations:
6.9K
Organization
View more organizations
Cited Papers
ShareSaveShareSaveShareSaveShareSaveShareSaveSemantic segmentation of high-resolution remote sensing images using fully convolutional network with adaptive threshold.png)
CONNECTION SCIENCE
CONNECTION SCIENCEIF3.4
PREAI
ShareSave View more