Abstract
Urbanization of watersheds is known to increase the flood risk potentials. Since 1970, eastern Jeddah, Saudi Arabia, underwent rapid urbanization due to the high rate of population growth and the booming economy, which attracts hundreds of thousands of expatriates. Such urbanizations change drastically the flood characteristics and enhance the risk from such watersheds as shown in 2009 and 2011 severe floods. To investigate the general relationship between the increases in flood peaks following historical urbanization in eastern Jeddah watersheds, satellite remote sensing data and meteorological data are developed. The utilization of high-resolution remote sensing data in temporal data analysis resulted in high classification accuracies using support vector machine as a classifier algorithm. The study area was classified into five different types of land use/land cover to quantify the changes that occurred between the bare rock and bare soil land cover classes. Three different data sets of images were synchronized with rainfall records, and hydrological data are used via watershed modeling systems. Such models are also used to obtain a quantitative estimate of the current potential risks. It is concluded that on average, the peak flows and the volumes increased by about 119% and about 89%, respectively.