الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 228 |  |  |
| | | from | 228 | | |
Abstract
”This research selects Egypt, which is severely water-deficient, as the research area, and takes the two most important crops (wheat and maize) in the region as the research object. With the goal of sustainable utilization, a green and blue water footprint assessment method for crops that satisfies water resource management is established. Based on artificial neural network (ANN), the spatiotemporal dynamic simulation of crop blue and green water footprint is carried out. The crop evapotranspiration prediction model under changing scenarios, and the deep learning network is used to simulate and predict the water footprint of the Nile Delta (2022-2040). The research will provide a scientific reference for the sustainable use of water sources and water-saving management in Egypt. The main research contents and results of the thesis are as follows : One of the research’s main contents is first to obtain the Green and Blue Water Evapotranspiration (GWET and BWET), which is essential keys to manage the various resources of water and simultaneously increase water-productivity. In Nile Delta over 1997-2017, altogether thirteen regions were chosen from three governorates as case studies. For estimating the reference evapotranspiration (ETo) and rainfall quantities, monthly datasets were obtained from freely-available-data. For these areas, GWET and BWET were computed and mapped for each region in the ArcGIS environment. Besides, the land use land cover (LULC) was extracted from Landsat images during different periods of 1997, 2005, 2011, and 2017. Analysis of GWET, BWET, and LULC showed that the best regions for saving green and blue water were Sidi-Salim, Bilqas, Ar-Riyad, Al-Hamul, and Biyala. The total water-saved was 4.80% and 53.12% of blue-green-water accounts. It can be concluded that data integration of GIS and LULC changes analysis is the best way for water-management and sustainable agro-system development under limited water resources. The second part was to model the green and blue water footprints (WFg and WFb) using ANNs as a superlative decision tool for making proper agricultural policy decisions to improving water use efficiency. Monthly meteorological datasets (minimum-temperature, maximum-temperature, precipitation, solar-radiation, soil-moisture, wind-speed, and vapor-pressure-deficit) were collected over the period (2006-2016). The analyzed data were divided into two parts from 2006 to 2012 and from 2013 to 2016 as model training and testing, respectively. The calculated WF values achieved a high statistical significance versus those simulated with the lowest distributional variations. Moreover, concerning model testing, findings indicated that the deviations between actual-predicted values ranged from -2.6 to 6.63% and from -2.4 to 3.16% for WFb and WFg, respectively. The established model will help to promote scientific water resource management and utilization. Finally, this research simulates and predicts the future (2022-2040) water footprint and yield of the Nile Delta based on a deep learning network. Outcomes displayed that the coefficient of determination for maize-wheat between historical-predicted ETc ranged from 0.92 to 0.97. A clear reduction in western and eastern wheat green WF (i.e. 24.96 and 37.44%) was caused by considerable variations in rainfall. It also induced a decrease in western maize of 103.93% and a growth in eastern of 8.96%. Moreover, increasing ETc by 8.46% and 12.45% gave rise to substantially growing 8.96% and 17.21%) for wheat and maize in the western compared to the east for blue-WF, respectively. The results also suggest a rise of grey-WF for wheat and maize by 3.07 and 5.02% in the west as associated with -14.51% and 12.37% in the east. Therefore, the outcomes powerfully recommend that 16.58% and 40.25% of total blue-water necessities for wheat-maize be decreased by the optimum usage of the eastern delta compared with others. The research results will provide scientific ideas for the agricultural sector to manage various water resources in response to climate change.