Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Comment on “The use of artificial neural networks for the prediction of water quality parameters” by H. R. Maier and G. C. Dandy

Comment on “The use of artificial neural networks for the prediction of water quality parameters”... use of artificial neural networks for the prediction of water quality parameters" by H. R. Maier and G. C. Dandy Vincent Fortin, Taha B. M. J. Ouarda, and Bernard Bob6e Institut National de la RechercheScientifique, Sainte-Foy,Qu6bec,Canada Nonparametricapproaches predictionand forecastingof to complexphysicalsystems, such as artificial neural networks (ANNs), are setto spread with moderncomputing possibilities. As Maier and Dandy [1996] correctlypoint out, data-driven models make prediction and forecastingpossibleunder less stringenthypotheses. This paper is highly appreciatedfor introducingANNs to the water resources communityand presentinga practicalapplication. However,asmanyreadersmay be unfamiliarwith this type of model,we would like to clarify links that existbetweenANNs and autoregressive-moving average(ARMA) models, whichthe authorsdid not emphasize. We would also like to suggest use of a different network the configuration, which may prove more appropriate for time seriesforecasting. To discuss the links that exist between ANNs and ARMA as they do not allow for knowledgeextractionin the form of rules... ". By themselves, ANNs are not appropriatefor acquiringand organizing knowledge can be usefulas part of but a largerautomated learningsystem [Mogiliand Sunol,1993].In short, there is nothing mysticalabout an artificial neural network, and usingAT terminologysustains hope that ANNs the maybe almostas efficientashumansin pickingup patternsin data, which is still far from the truth. When properly used http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Water Resources Research Wiley

Comment on “The use of artificial neural networks for the prediction of water quality parameters” by H. R. Maier and G. C. Dandy

Loading next page...
 
/lp/wiley/comment-on-the-use-of-artificial-neural-networks-for-the-prediction-of-DO0sNR0p8E

References (20)

Publisher
Wiley
Copyright
Copyright © 1997 by the American Grophysical Union.
ISSN
0043-1397
eISSN
1944-7973
DOI
10.1029/97WR00969
Publisher site
See Article on Publisher Site

Abstract

use of artificial neural networks for the prediction of water quality parameters" by H. R. Maier and G. C. Dandy Vincent Fortin, Taha B. M. J. Ouarda, and Bernard Bob6e Institut National de la RechercheScientifique, Sainte-Foy,Qu6bec,Canada Nonparametricapproaches predictionand forecastingof to complexphysicalsystems, such as artificial neural networks (ANNs), are setto spread with moderncomputing possibilities. As Maier and Dandy [1996] correctlypoint out, data-driven models make prediction and forecastingpossibleunder less stringenthypotheses. This paper is highly appreciatedfor introducingANNs to the water resources communityand presentinga practicalapplication. However,asmanyreadersmay be unfamiliarwith this type of model,we would like to clarify links that existbetweenANNs and autoregressive-moving average(ARMA) models, whichthe authorsdid not emphasize. We would also like to suggest use of a different network the configuration, which may prove more appropriate for time seriesforecasting. To discuss the links that exist between ANNs and ARMA as they do not allow for knowledgeextractionin the form of rules... ". By themselves, ANNs are not appropriatefor acquiringand organizing knowledge can be usefulas part of but a largerautomated learningsystem [Mogiliand Sunol,1993].In short, there is nothing mysticalabout an artificial neural network, and usingAT terminologysustains hope that ANNs the maybe almostas efficientashumansin pickingup patternsin data, which is still far from the truth. When properly used

Journal

Water Resources ResearchWiley

Published: Oct 1, 1997

There are no references for this article.