Show simple item record

dc.contributor.author Zealand, Cameron M. en_US
dc.date.accessioned 2007-05-15T15:27:22Z
dc.date.available 2007-05-15T15:27:22Z
dc.date.issued 1997-07-01T00:00:00Z en_US
dc.identifier.uri http://hdl.handle.net/1993/1054
dc.description.abstract Many of the activities associated with the planning and operation of water resource systems require forecasts of future events. For the hydrologic component that forms the input for water resource systems, there is a need for both short term and long term forecasts of streamflow events in order to optimize the real-time operation of the system or to plan for future expansion. The main objective of this research is to investigate the utility of Artificial Neural Networks (ANNs) for short term forecasting of streamflow. Short term is defined as weekly time steps up to a time horizon of one month ahead. The work explores the capabilities of ANNs and compares the performance of this tool to conventional approaches used to forecast streamflow events one, two, three and four weeks in advance. A number of issues associated with the configuration of the ANN are examined to determine the preferred approach for implementing this technology in the forecasting mode. The performance of the ANN for the forecasting task is evaluated for a range of streamflow conditions in order to test the capabilities of ANNs in a realistic setting. The capabilities of the ANN model are compared to those of more traditional forecasting methods to ascertain the relative merits of each approach. ANNs have been found to be effective in situations with noisy data. A perceived strength of ANNs is the capability for representing complex, nonlinear relationships as well as being able to model interaction effects. (Abstract shortened by UMI.) en_US
dc.format.extent 8335049 bytes
dc.format.extent 184 bytes
dc.format.mimetype application/pdf
dc.format.mimetype text/plain
dc.language en en_US
dc.language.iso en_US
dc.rights info:eu-repo/semantics/openAccess
dc.title Short-term streamflow forecasting using artificial neural networks en_US
dc.type info:eu-repo/semantics/masterThesis
dc.degree.discipline Civil Engineering en_US
dc.degree.level Master of Science (M.Sc.) en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

View Statistics