| It has become very crucial to manage water resources to meet the needs of the growing population. In irrigation command areas, and in order to build a better plan to manage service delivery from canals and reservoirs, it is important to build appropriate knowledge of water needs on a field basis. There is often a lag between the order and delivery of water to the field. Knowledge of the crop water requirement at the field level helps the decision maker to make the right choices leading to more efficient handling of the available water. The purpose of this study was to develop methodologies and tools that allow better management of irrigation water and water delivery systems, such as machine learning models that can be used as tools for decision support systems of water management. To achieve better modeling and prediction, wavelet decompositions were explored for their ability to give information about time and frequency changes in the data. Remote sensing approaches were also used for their ability to quantify water requirements at the spatial level. Therefore, this dissertation explored the use of the above-mentioned data tools and techniques to address water management problems. The framework of this dissertation consisted of three components that provide tools to support irrigation system operational decisions. In general, the results for each of the methods developed were satisfactory, relevant, and encouraging. They provided significant potential for improving decision making for real-time applications in irrigation command areas and better management of the water resources. |
