Forecasting water demand for future urban expansion using artificial neural network and geo-informatics techniques | |
| Author | Kuanput Ngosuwan |
| Call Number | AIT Thesis no.RS-11-11 |
| Subject(s) | Municipal water supply--Forecasting--Geographic information systems--Thailand--Samut Sakhon Water consumption--Forecasting--Geographic information systems--Thailand--Samut Sakhon |
| Note | A thesis submitted in pa1iial fulfillment of the requirements for The degree of Master of Science Remote Sensing and Geographic Information Systems, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. RS-11-11 |
| Abstract | The rapid increasing of urban area and population growth rate exceeds by far the rate of developing water resources. Therefore, it is important to predict the amount of urban water consumption in next scenario to planning and managing water supply. The urban water demand of any city is a complex and it is influence on many variables such as meteorological, socioeconomic and management variable. However, as per rate of urbanizations and water demand there is really need to use some advanced technology which can overcome all the limitation of traditional methods. The combination of satellite remote sensing, Geographical Information Systems (GIS) and urban water prediction models by Artificial Neural Network (ANN) can gives accurate water demand for the service areas of Provincial Waterworks Authority (PWA). The main objective of this study was to explore an urban area since year 2002 to year 2010. The total urban area in each year is the input parameter of ANN model to forecasting urban water demand. In the study area was classified into three sectors types which definition by PW A as; residential sector, small-business and governmental sector, and state enterprise and large-business sector. The study implemented the three models and combined it into total sales sector for next 10 years period for whole services area and by sub district. Results of water demand for PWA provide a forecasting accuracy more than 96%. For whole services area model GPP per Capita and population are the most sensitive variable while population and number of household affect on sub district mode. Moreover, population and number of househould have highly significant for residential sector. Furthermore, population density, GPPC and Built up area were the most significant impact on government and small business sector. In addition, population and built up area are the most sensitive variable for whole services area while GPP is the most sensitive variables for sub district. In sub district level, Tha Sai, Na Di and Bang Krachao are the most required water demand as a result of industrial area. While, Phan Thai Norasing was following the trend of residential city. However, MaHa Chai and Suan Luang sub district are the least required water consumption although there are industrial areas as result from using underground water. In addition, residential area is support by municipal water supply. The results of this study should assist the PW A making the right decisions for operation and investment in this area. |
| Year | 2011 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. RS-11-11 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Tripathi, Nitin Kumar |
| Examination Committee(s) | Sutat Weesakul; Taravudh Tipdecho |
| Scholarship Donor(s) | Provincial Waterworks Authority, Thailand;Royal Thai Government Fellowship |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 2011 |