Institute: District of Columbia
Year Established: 2016 Start Date: 2016-03-01 End Date: 2017-02-28
Total Federal Funds: $9,779 Total Non-Federal Funds: $19,663
Principal Investigators: Nian Zhang, Pradeep Behera
Abstract: Prediction of river stage has been an interesting research topic in hydrologic engineering, from water supply, flood forecasting, and water quantity and quality management viewpoint. For example, long-term evaluation on the potential impact of climate change on the water supply resources of the Washington, D.C., metropolitan area is very important. In order to predict the future river stage based on the current information is very much necessary for water supply managers. The proposed nearest-neighbor method (NNM) will significantly increase the prediction accuracy on water quantity prediction problem. It will be the first time for the proposed extended nearest-neighbor (ENN) method to predict hydrologic time series, which can then be tailed to solve the streamflow prediction problem. The proposed cosine angle distance (CAD) is a promising popular distance measure that will help improve the prediction accuracy in the nearest-neighbor method (NNM). This has not been used in streamflow quantity prediction problem. A highly motivated computer science graduate student will be involved in the project. The project will be used as the graduate student’s master thesis project. Through working on the project the student will become familiar with the aspects of stormwater management, computational intelligence theory and its application to time series prediction for stormwater streamflow data. The development of the methods benefit to the students as they can be used for demonstration of computational intelligence analysis. Seminar will be arranged to show the outcome of the research to students at UDC.