skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Predicting stream water quality using artificial neural networks (ANN)

Abstract

Predicting point and nonpoint source runoff of dissolved and suspended materials into their receiving streams is important to protecting water quality and traditionally has been modeled using deterministic or statistical methods. The purpose of this study was to predict water quality in small streams using an Artificial Neural Network (ANN). The selected input variables were local precipitation, stream flow rates and turbidity for the initial prediction of suspended solids in the stream. A single hidden-layer feedforward neural network using backpropagation learning algorithms was developed with a detailed analysis of model design of those factors affecting successful implementation of the model. All features of a feedforward neural model were investigated including training set creation, number and layers of neurons, neural activation functions, and backpropagation algorithms. Least-squares regression was used to compare model predictions with test data sets. Most of the model configurations offered excellent predictive capabilities. Using either the logistic or the hyperbolic tangent neural activation function did not significantly affect predicted results. This was also true for the two learning algorithms tested, the Levenberg-Marquardt and Polak-Ribiere conjugate-gradient descent methods. The most important step during model development and training was the representative selection of data records for training of the model.

Authors:
Publication Date:
Research Org.:
Savannah River Site (US)
Sponsoring Org.:
US Department of Energy (US)
OSTI Identifier:
755373
Report Number(s):
WSRC-MS-2000-00112
TRN: AH200016%%123
DOE Contract Number:  
AC09-96SR18500
Resource Type:
Conference
Resource Relation:
Conference: Envirosoft 2000, Bilbao (ES), 06/28/2000--06/30/2000; Other Information: PBD: 17 May 2000
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; WATER POLLUTION; STREAMS; RUNOFF; POLLUTION SOURCES; ALGORITHMS; NEURAL NETWORKS; FORECASTING

Citation Formats

Bowers, J.A. Predicting stream water quality using artificial neural networks (ANN). United States: N. p., 2000. Web.
Bowers, J.A. Predicting stream water quality using artificial neural networks (ANN). United States.
Bowers, J.A. Wed . "Predicting stream water quality using artificial neural networks (ANN)". United States. https://www.osti.gov/servlets/purl/755373.
@article{osti_755373,
title = {Predicting stream water quality using artificial neural networks (ANN)},
author = {Bowers, J.A.},
abstractNote = {Predicting point and nonpoint source runoff of dissolved and suspended materials into their receiving streams is important to protecting water quality and traditionally has been modeled using deterministic or statistical methods. The purpose of this study was to predict water quality in small streams using an Artificial Neural Network (ANN). The selected input variables were local precipitation, stream flow rates and turbidity for the initial prediction of suspended solids in the stream. A single hidden-layer feedforward neural network using backpropagation learning algorithms was developed with a detailed analysis of model design of those factors affecting successful implementation of the model. All features of a feedforward neural model were investigated including training set creation, number and layers of neurons, neural activation functions, and backpropagation algorithms. Least-squares regression was used to compare model predictions with test data sets. Most of the model configurations offered excellent predictive capabilities. Using either the logistic or the hyperbolic tangent neural activation function did not significantly affect predicted results. This was also true for the two learning algorithms tested, the Levenberg-Marquardt and Polak-Ribiere conjugate-gradient descent methods. The most important step during model development and training was the representative selection of data records for training of the model.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2000},
month = {5}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: