Adaptive hydrological flow field modeling based on water body extraction and surface information

Suranaree University of Technology, School of Computer Engineering,111 University Avenue, Muang, Nakhon Ratchasima 30000, ThailandAbstract. Hydrological flow characteristic is one of the prime indicators for assessing flood.It plays a major part in determining drainage capability of the affected basin and also in thesubsequent simulation and rainfall-runoff prediction. Thus far, flow directions were typicallyderived from terrain data which for flat landscapes are obscured by other man-made structures,hence undermining the practical potential. In the absence (or diminutive) of terrain slopes, waterpassageshaveamorepronouncedeffectonflowdirectionsthanelevations.Thispaper,therefore,presents detailed analyses and implementation of hydrological flow modeling from satellite andtopographicimages.Herein,gradualassignmentbasedonsupportvectormachinewasappliedtomodified normalized difference water index and a digital surface model, in order to ensure reli-able water labeling while suppressing modality-inherited artifacts and noise. Gradient vectorflow was subsequently employed to reconstruct the flow field. Experiments comparing theproposed scheme with conventional water boundary delineation and flow reconstruction werepresented. Respective assessments revealed its advantage over the generic stream burning.Specifically, it could extract water body from studied areas with 98.70% precision, 99.83%recall, 98.76% accuracy, and 99.26% F-measure. The correlations between resultant flowsand those obtained from the stream burning were as high as 0.80 0.04 (p ≤ 0.01 in all res-olutions).