Skip to main content

GIS-Based Artificial Neural Network and Processed-Based HSPF Model for Watershed Runoff in Sinclair and Dyes Inlet, WA

Buy Article:

$9.50 plus tax (Refund Policy)

Or sign up for a free trial

Sinclair Inlet and Dyes Inlet are two inter-connected sub-estuaries of the Puget Sound estuarine system, located in the region of (−122° 43', 47° 39') and (−122° 37', 47° 32'), north of Bremerton, WA. Pacific Ocean tides enter through the mouth of the Puget Sound and propagate to both Inlets from Brownsville, to the north and Clam Bay, to the South. The Inlets receive freshwater inflows and land-based contaminant loadings from industrial and stormwater discharges, sewage treatment plants and runoff from the surrounding watersheds. As part of a Total Maximum Daily Load (TMDL) modeling study, which is collaboratively supported by an agreement among the Puget Sound Naval Shipyard (PSNS), the Environmental Protection Agency (EPA), and the Washington State Department of Ecology, the watershed model HSPF (Hydrologic Simulation Program-FORTRAN), is currently being used to quantify runoff from eleven basins draining into the two Inlets.

While the HSPF models provide hydrographs and pollutographs, the model development and calibration for the eleven watersheds is nontrivial, let alone the large amount of field data required for model calibration. As such, a simple, and computationally fast model using an Artificial Neural Network (ANN) was developed to predict relationships between precipitation and freshwater inflows to the Inlets. The ANN uses a feed-forward, back-propagating neural network and consists of three layers: an input layer, hidden layer, and output layer. The ANN model uses a finite number of input nodes representing precipitation prior to the time of prediction. The ANN model is trained using the measured creekflow data and the corresponding precipitation data. With a back-propagation algorithm, the training optimizes the two weighting function matrices between the input and hidden layers as well as the hidden and output layers. With adequate training (learning), the ANN model is then capable of predicting creekflow resulting from precipitation. ANN-predicted flows for 3 creeks are compared with those predicted by the HSPF model. Results of both the ANN model and the process-based HSPF model bear similar accuracy levels. Considering the cost/product factor, this study shows that the ANN modeling approach provides a cost-effective alternative tool for predicting rainfall-runoff relationships.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Document Type: Research Article

Publication date: 2002-01-01

More about this publication?
  • Proceedings of the Water Environment Federation is an archive of papers published in the proceedings of the annual Water Environment Federation® Technical Exhibition and Conference (WEFTEC® ) and specialty conferences held since the year 2000. These proceedings are not peer reviewed.

    A subscription to the Proceedings of the Water Environment Federation includes access to most papers presented at the annual WEF Technical Exhibition and Conference (WEFTEC) and other conferences held since 2000. Subscription access begins 12 months after the event and is valid for 12 months from month of purchase. A subscription to the Proceedings of the Water Environment Federation is included in Water Environment Federation (WEF) membership.

    WEF Members: Sign in (right panel) with your IngentaConnect user name and password to receive complimentary access. Access begins 12 months after the conference or event
  • Subscribe to this Title
  • Membership Information
  • About WEF Proceedings
  • WEFTEC Conference Information
  • Learn about the many other WEF member benefits and join today
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more