Development of a decision support system for drought characterization and management

A decision support system has been developed, capable of running on a personal computer, which will assist water managers and decision makers in making optimal decisions during drought conditions. There are three major components of the developed decision support system: (1) a demand forecasting component, (2) a streamflow forecasting component, and (3) an integrated expert system component. Several model structures were investigated for use in forecasting both demand and streamflow. This research effort has revealed that the new technology of Expert Systems can be a very effective tool to facilitate and improve drought characterization and management. This research effort has also concluded that the emerging technology of Artificial Neural Networks (ANN) can be used to forecast municipal water use with better accuracy than traditional methods, such as, time series or regression analysis. Data derived from the city of Lexington, Kentucky and the Kentucky River Basin were used to test the developed decision support system. A new concept of synthetically generating total rainfalls from a known streamflow series using a conceptual rainfall runoff model in a reverse direction has also been proposed.