Real-Time Forecasting of River Flow for Water Supply Operation
Publication: Critical Transitions in Water and Environmental Resources Management
Abstract
Tampa Bay Water, a wholesale water supplier, provides about 200 MGD of groundwater to assist in meeting potable water needs of nearly 2 million people in the Tampa Bay area of Florida. Under the current Consolidated Permit, Tampa Bay Water is required to cut back groundwater pumpage from 11 regional wellfields in phases. The reduction amount will be compensated by the enhanced surface water system withdrawing from three sources including the Tampa Bypass Canal (TBC), Alafia River and Hillsborough River. Artificial Neural Networks (ANNs) have been developed to forecast daily river flows at key points at selected flow gages in the upper and middle basins of the Hillsborough river. The multilayer backpropagation ANNs are designed to mimic the governing physical equations (e.g. continuity equation and energy balance), which use initial and boundary conditions to predict future system states. Furthermore, the ANNs inputs include terms that reflect the autocorrelation properties of the underlying time series. About 13 years of daily data were used to train and test the ANN models. The fitted networks utilized about 70% of the data for training while the rest was reserved for testing and validation. Testing results indicated that the trained ANNs provide highly accurate predictions for daily flows over the next seven days.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
Information & Authors
Information
Published In
Copyright
© 2004 American Society of Civil Engineers.
History
Published online: Apr 26, 2012
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.