.png){kind=icon}
.png){kind=icon}
Return
Flood risk modeling for Kisumu County; Kenya: integrating multi-source geospatial data and machine learning
.png){kind=icon}
OA
AI
H
M
A
DOI：10.3389/fenvs.2026.1829199.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
IntroductionFlooding poses an escalating threat to Kisumu County; Kenya; driven by climate change and rapid urbanization.MethodsThis study develops an integrated framework combining remote sensing; GIS; and machine learning for flood risk mapping and forecasting using multi‐source geospatial data (Sentinel‐1 SAR; Landsat 8; SRTM DEM; SMAP soil moisture) and meteorological data (2014‐2025). Four machine learning models random forest (RF); artificial neural network (ANN); deep neural network (DNN); and convolutional neural network (CNN) were developed and validated.ResultsThe ANN achieved the highest accuracy (R2 = 0.910; RMSE = 0.038). Excluding RF (R2 = 0.520) from the ensemble improved performance to R2 = 0.916 (RMSE = 0.035); a 22% error reduction. Flood risk mapping classified Kisumu County into five categories; revealing that 40.9% (857.8 km2) faces moderate to very high risk; with critical hotspots along the Lake Victoria shoreline and in Kisumu City and Ahero. Slope (20%); NDBI (15%); soil moisture (15%); and stream proximity (15%) were identified as dominant flood drivers. Uncertainty quantification revealed low model variance (R2 σ = 0.006) and demonstrated that aleatoric uncertainty (62%) dominates epistemic uncertainty (38%).Discussion/ConclusionThis framework provides a replicable; data‐driven methodology for flood risk assessment in data‐scarce regions globally.
Keywords:
uncertainty quantification
remote sensing
GIS
ensemble methods for classification
flood risk modeling
Lake Victoria (East Africa)
machine learning-based classification
Journal
IF:
3.7
Papers:
7.9K
Citations:
2.3W
Organization
Cited Papers