Urban Annual Water Consumption Prediction Using Artificial Neural Network

Bo Liang

doi:10.4028/www.scientific.net/AMM.409-410.1008

Paper Titles

An Analysis on the Urban Flood Control
p.991

Alternative Solutions for Sustainable Urban Drainage Systems Integrating Areas of Irregular Urban Growth with the Formal City
p.996

Weighting of Performance Index by Analytic Hierarchy Process for Water Supply Enterprises
p.1004

Urban Annual Water Consumption Prediction Using Artificial Neural Network
p.1008

Design of Large Closed Loop Control Structure for Urban Drainage Systems in the Whole Optimizing Running Process
p.1012

Evolvement and Characteristic of Urban Spatial Structure in Baotou
p.1017

The Influences of the High-Rise Buildings to Urban Space Morphology in Chongqing
p.1021

Correlation Study of Urban Plaza Environment and Behavior Based on GPS
p.1026

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 409-410Urban Annual Water Consumption Prediction Using...

Urban Annual Water Consumption Prediction Using Artificial Neural Network

Abstract:

The paper established the BP neural network to predict the annual water consumption. The consumption of Tianjin urban annual water from 1991 to 2007 and its related factors including the urban population, per capita income levels, industrial output value, the city GDP, per capita daily water consumption, industrial water recycling rate are analyzed. The results show that the average deviations are 1.03%, 1.61%, and 1.26% for the hidden layer neuron number 10, 15 and 20 respectively for BP prediction. The R² value reached to 0.9587, 0.8058, and 0.8851 for the hidden layer neuron number 10, 15 and 20 respectively for BP prediction. This confirms high efficiency for the hidden layer neuron number 10 in BP prediction.

You might also be interested in these eBooks

Sustainable Development and Environment II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 409-410)

Pages:

1008-1011

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.409-410.1008

Citation:

Cite this paper

Online since:

September 2013

Authors:

Bo Liang

Keywords:

BP Neural Network (BPNN), Hidden Layer Neuron, Water Consumption

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WANG Q, HELLER M. Hybrid box-jenkins and neural network forecasting of potable water demand [C]/ / Proceedings of the 1996 Artificial Neural Networks in Engineering ANNIE[J]. Missouri: ASME, 1996: 801-807.

Google Scholar

[2] Orit Wilchfort and Jay R Lund. Shorting management modeling for urban water supply systems[J]. Journal of Water Resource Planning and Management, 1999, 123(4): 250-258.

DOI: 10.1061/(asce)0733-9496(1997)123:4(250)

Google Scholar

[3] Razi, M.A., Athappilly, K. A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models[J]. Expert Systems with Applications, 2005, 29: 65-74.

DOI: 10.1016/j.eswa.2005.01.006

Google Scholar

[4] Ward, J.V., Tockner, K., Arscott, D.B., Claret, C. Riverine landscape diversity[J]. Freshwater Biology, 2002, 47: 517-539.

DOI: 10.1046/j.1365-2427.2002.00893.x

Google Scholar

[5] Chelani, A.B., Gajghate, D.G., Hasan, M.Z. Prediction ofambient PM10 and toxic metals using artificial neural networks[J]. Journal of the Air and Waste Management Association, 2002, 52, 805-810.

DOI: 10.1080/10473289.2002.10470827

Google Scholar

[6] Ramadan Z., Hopke P.K., Johnson M.J., Scow K. M. Application of PLS and back-propagation neural networks for the estimation of soil properties[J]. Chemometrics Intell Lab Syst, 2005, 75: 23-30.

DOI: 10.1016/j.chemolab.2004.04.009

Google Scholar