Disasters caused by floods are a major cause of losses of properties and lives. The unpredictability in weather conditions due to changing weather patterns do not only lead to flooding but also contribute to water resource management problems. Rapid development in many tropical countries, like in Malaysia, has resulted in the loss of natural floodplains leading to an increase in flooding and water shortage. Sufficient advanced flood warning system that can save lives and properties can be developed using accurate river model. The work reported in this thesis has made significant contributions in the prediction of river flow rate based on rainfall rate in the catchment area using Artificial Neural Network (ANN). The proposed approach models the non-linear process of the rainfall-runoff in a wide variety of catchment area conditions. This study demonstrates significant improvement in the accuracy and reliability of water resource management by using ANN modelling to predict river flow rate. It also shows ANN as a fast and adaptable approach that is suitable for river flow rate modelling that does not need detailed geographical information of the catchment area. Its attractiveness is in its ability to adapt to changing conditions and therefore does not become outdated like conventional hydrology models. The research shows that river flow rate is a better parameter to be used for an early flood warning system as it is more sensitive to rainfall rate compared to the river level which is used in conventional flood warning systems. The study has also shown that ANN with a feed-backward network with one hidden layer provides the best results and it is able to produce river flow rate prediction up to 132 hours with root mean square error of 0.02 m<sup>3</sup>/s . This is a significant contribution as the flood warning system currently used in Malaysia can only predict flooding within 8 to 24 hours. The work in this thesis can assist the authorities to manage water from dams thereby effectively managing floods and ensuring sufficient water for domestic and agricultural use. The findings of this research has already been presented to the Malaysian government agency responsible for managing waterways and dams.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:749223 |
| Date | January 2017 |
| Creators | Noor, Hassanuddin Mohamed |
| Publisher | University of Portsmouth |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Source | https://researchportal.port.ac.uk/portal/en/theses/artificial-neural-network-application-in-water-resources-management-and-flood-warning(5a22f4f9-55d0-484f-9dfb-22a0a7e085dc).html |
Page generated in 0.0739 seconds