Artificial neural network simulation of combined permeable pavement and earth energy systems treating storm water

Kiran Tota-Maharaj, Miklas Scholz

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Artificial intelligence techniques, such as neural networks, are modeling tools that can be applied to analyze urban runoff quality issues. Artificial neural networks are frequently used to model various highly variable and nonlinear physical phenomena in the water and environmental engineering fields. The application of neural networks for analyzing the performance of combined permeable pavement and earth energy systems is timely and novel. This paper presents the application of back-propagation neural networks and the testing of the Levenberg-Marquardt, Quasi-Newton, and Bayesian Regularization algorithms. The neural networks were statistically assessed for their goodness of prediction with respect to the biochemical oxygen demand (BOD), ammonia-nitrogen, nitrate-nitrogen, and ortho-phosphate-phosphorus by numerical computation of the mean absolute error, root-mean-square error, mean absolute relative error, and the coefficient of correlation for the prediction compared with the corresponding measured data. The three neural network models were assessed for their efficiency in accurately simulating the effluent water quality parameters from various experimental pavement systems. The models predicted all key parameters with high correlation coefficients and low minimum statistical errors. The back-propagation and feed-forward neural network models performed optimally as pollutant removal predictors with regard to these two sustainable technologies.
Original languageEnglish
Pages (from-to)499-509
Number of pages11
JournalJournal of Environmental Engineering
Volume138
Issue number4
DOIs
Publication statusPublished - Apr 2012
Externally publishedYes

Fingerprint

pavement
artificial neural network
back propagation
simulation
energy
water
physical phenomena
pollutant removal
artificial intelligence
nitrogen
orthophosphate
biochemical oxygen demand
prediction
ammonia
effluent
runoff
nitrate
phosphorus
water quality
modeling

Cite this

@article{d502502347e446b09e27b6bd7b893cc5,
title = "Artificial neural network simulation of combined permeable pavement and earth energy systems treating storm water",
abstract = "Artificial intelligence techniques, such as neural networks, are modeling tools that can be applied to analyze urban runoff quality issues. Artificial neural networks are frequently used to model various highly variable and nonlinear physical phenomena in the water and environmental engineering fields. The application of neural networks for analyzing the performance of combined permeable pavement and earth energy systems is timely and novel. This paper presents the application of back-propagation neural networks and the testing of the Levenberg-Marquardt, Quasi-Newton, and Bayesian Regularization algorithms. The neural networks were statistically assessed for their goodness of prediction with respect to the biochemical oxygen demand (BOD), ammonia-nitrogen, nitrate-nitrogen, and ortho-phosphate-phosphorus by numerical computation of the mean absolute error, root-mean-square error, mean absolute relative error, and the coefficient of correlation for the prediction compared with the corresponding measured data. The three neural network models were assessed for their efficiency in accurately simulating the effluent water quality parameters from various experimental pavement systems. The models predicted all key parameters with high correlation coefficients and low minimum statistical errors. The back-propagation and feed-forward neural network models performed optimally as pollutant removal predictors with regard to these two sustainable technologies.",
author = "Kiran Tota-Maharaj and Miklas Scholz",
year = "2012",
month = "4",
doi = "10.1061/(ASCE)EE.1943-7870.0000497",
language = "English",
volume = "138",
pages = "499--509",
journal = "Journal of Environmental Engineering",
number = "4",

}

Artificial neural network simulation of combined permeable pavement and earth energy systems treating storm water. / Tota-Maharaj, Kiran; Scholz, Miklas.

In: Journal of Environmental Engineering, Vol. 138, No. 4, 04.2012, p. 499-509.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial neural network simulation of combined permeable pavement and earth energy systems treating storm water

AU - Tota-Maharaj, Kiran

AU - Scholz, Miklas

PY - 2012/4

Y1 - 2012/4

N2 - Artificial intelligence techniques, such as neural networks, are modeling tools that can be applied to analyze urban runoff quality issues. Artificial neural networks are frequently used to model various highly variable and nonlinear physical phenomena in the water and environmental engineering fields. The application of neural networks for analyzing the performance of combined permeable pavement and earth energy systems is timely and novel. This paper presents the application of back-propagation neural networks and the testing of the Levenberg-Marquardt, Quasi-Newton, and Bayesian Regularization algorithms. The neural networks were statistically assessed for their goodness of prediction with respect to the biochemical oxygen demand (BOD), ammonia-nitrogen, nitrate-nitrogen, and ortho-phosphate-phosphorus by numerical computation of the mean absolute error, root-mean-square error, mean absolute relative error, and the coefficient of correlation for the prediction compared with the corresponding measured data. The three neural network models were assessed for their efficiency in accurately simulating the effluent water quality parameters from various experimental pavement systems. The models predicted all key parameters with high correlation coefficients and low minimum statistical errors. The back-propagation and feed-forward neural network models performed optimally as pollutant removal predictors with regard to these two sustainable technologies.

AB - Artificial intelligence techniques, such as neural networks, are modeling tools that can be applied to analyze urban runoff quality issues. Artificial neural networks are frequently used to model various highly variable and nonlinear physical phenomena in the water and environmental engineering fields. The application of neural networks for analyzing the performance of combined permeable pavement and earth energy systems is timely and novel. This paper presents the application of back-propagation neural networks and the testing of the Levenberg-Marquardt, Quasi-Newton, and Bayesian Regularization algorithms. The neural networks were statistically assessed for their goodness of prediction with respect to the biochemical oxygen demand (BOD), ammonia-nitrogen, nitrate-nitrogen, and ortho-phosphate-phosphorus by numerical computation of the mean absolute error, root-mean-square error, mean absolute relative error, and the coefficient of correlation for the prediction compared with the corresponding measured data. The three neural network models were assessed for their efficiency in accurately simulating the effluent water quality parameters from various experimental pavement systems. The models predicted all key parameters with high correlation coefficients and low minimum statistical errors. The back-propagation and feed-forward neural network models performed optimally as pollutant removal predictors with regard to these two sustainable technologies.

U2 - 10.1061/(ASCE)EE.1943-7870.0000497

DO - 10.1061/(ASCE)EE.1943-7870.0000497

M3 - Article

VL - 138

SP - 499

EP - 509

JO - Journal of Environmental Engineering

JF - Journal of Environmental Engineering

IS - 4

ER -