Remote Sensing, Vol. 14, Pages 2465: An Extended Watershed-Based AHP Model for Flood Hazard Estimation: Constraining Runoff Converging Indicators via MFD-Derived Sub-Watershed by Maximum Zonal Statistical Method (Remote Sensing)

Floods threaten the sustainable development of areas with a high probability of hazard. A typical analytic hierarchy process (pixel-based AHP) based flood hazard estimation method may ignore the similar threat caused by neighborhood cells at the sub-watershed scale. This study proposed an extended Watershed-based Zonal Statistical AHP for flood hazard estimation: Constraining converging related indicators by the sub-watersheds (WZSAHP-RC) model to improve this gap. Before calculating the flood hazard index, the proposed model uses the sub-watershed derived by the multiple flow direction method as a based unit to calculate the maximum zonal statistical value of runoff converging indicators. Moreover, taking the Chaohu basin of Anhui in China as the case study, the validation flooding ground-truthing was constructed from GF-3, and Landsat OLI images of the flood event from 20 July to 24 July 2020, which is the biggest flood recorded by the Zhongmiao station, which recorded a new water level, 0.82 m higher than the historical record. Compared with the validation, the results indicated the proposed method could improve the correct ratio by 38% (from 22% to 60%) and the fit ratio by 17% (from 18% to 35%) when considering the predicted flood hazard levels of “High” and “Very High” as flooded areas. Moreover, the flood hazard map derived by WZSAHP-RC demonstrated greater consistency in the flooded districts filtered by Baidu News than the pixel-based AHP. It revealed that considering two- or even multi-dimensional homogeneity may help to improve the accuracy of flood hazard maps on a catchment scale.