Font Size: a A A

Exploring Water Use Patterns And Forecasting Water Consumption Along Transboundary Water Resources,for Water Resource Management

Posted on:2023-03-26Degree:DoctorType:Dissertation
Country:ChinaCandidate:M M u m b i A n n e W a Full Text:PDF
GTID:1520307316951649Subject:Environmental Science and Engineering
Abstract/Summary:PDF Full Text Request
Water resources are an essential component of the country’s natural resource potential.Pressure on these resources is set to increase due to increased water demand,climate change and rainfall variability.This could lead to conflicts between sectoral users,within or between countries especially among transboundary countries.Interest in transboundary water resources is a priority for ensuring water security and sustainable water use.Especially in cases where issues such as the continued uncertainty of the status of transboundary water bodies and water volume reduction persist.Noting the geopolitical implications of water demand and stress issues on water resources worldwide,this thesis investigated water demand,changes in water use patterns and water stress developments in the Nile Basin transboundary water resource by comparing Egypt and Kenya.The thesis mainly focuses on two studies aimed at addressing water demand issues along the Nile River.The first main study of the thesis juxtaposes the complex issue of water use,demand and the driving factors in two countries through the use of quantitative and qualitative analysis based on the triangulation method for data analysis.The findings demonstrate increased water withdrawals and a growing unmet demand in both countries.In addition to,changing water use patterns towards municipal and industrial use,hydropower development in Kenya and navigation in Egypt are being driven by factors such as heightened upstream use,population growth and settlement patterns,economic development and climate change.In addition,spatial distribution of water stress was demonstrated,whereby downstream countries such as Egypt remain critically vulnerable,although upper riparian countries such as Kenya are gradually also facing emerging water stress problems.This water stress and its spatial distribution are being driven by supply–demand imbalances related to population growth and economic development,escalating upstream water use,deteriorating water quality,inefficient and ineffective water use and climate change.The findings inform a discussion of the crucial socioeconomic,geopolitical and policy implications for riparian countries in the Nile Basin and other transboundary water resources worldwide.The second main study of the thesis focuses on;enhancing sustainable resource utilization of transboundary water bodies among the sharing countries and demonstrates the application of the feedforward neural network(FFNN)for water demand forecasting along the Nile River in two countries i.e.Egypt and Kenya that are characterized as water-scarce states in sub-Saharan Africa.A consumption prediction model was developed to predict water demand up to the year 2040 with computational algorithms for the models based on commercially available software.Both the recurrent neural network and the FFNN were tested for accuracy.The accuracy of the FFNN was higher compared to the RNN hence it was selected for the study.Two scenarios were modelled with input data for the first scenario including the preceding records of precipitation,gross domestic product,population,and water use in the agricultural sector.The second scenario observed the impacts of the growing economy on water resources by doubling the gross domestic product and having all the other inputs constant.For Kenya,the best results for the FFNN were obtained using 2 hidden layers with 30 hidden units each,with a learning rate of 0.01 and an L2 regularization parameter at 0.04.The results projected a steady increase in water demand throughout the next 20 years for both scenarios.For Egypt,the best results for the FFNN were obtained using 3 hidden layers with 50 hidden units each,with a learning rate of 0.01 and an L2 regularization parameter of 0.1,the observed trend was a decline in demand followed by a steady increase in both scenarios.The results underscore the importance of forecasting for easier future planning and management and indicate that FFNNs can be considered as alternate and practical tools in forecasting,which is particularly useful for assisting governing bodies along transboundary water resources to develop timely strategies over the future.In conclusion,the thesis highlights of the outlook have been expounded and paved new ways for addressing other natural resources and transboundary resources such as land.Through an explicit analysis of available data,strategies,policies and frameworks existent on the Nile River and the recommendations put forth.
Keywords/Search Tags:Feed-forward neural network, Nile River, transboundary resources, water demand, water stress
PDF Full Text Request
Related items