Prediction of sulphur dioxide concentration using artificial neural networks

A three-layer neural network model with a hidden recurrent layer is used to predict sulphur dioxide concentration and the predicted values are compared with the measured concentrations at three sites in Delhi. The Levenberg-Marquardt algorithm is used to train the network. The neural network is used...

Full description

Saved in:
Bibliographic Details
Published in:Environmental modelling & software : with environment data news 2002-01, Vol.17 (2), p.161-168
Main Authors: Chelani, AB, Rao, CVC, Phadke, K M, Hasan, M Z
Format: Article
Language:English
Subjects:
Algorithms
Computer simulation
Mathematical models
Neural networks
Regression analysis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A three-layer neural network model with a hidden recurrent layer is used to predict sulphur dioxide concentration and the predicted values are compared with the measured concentrations at three sites in Delhi. The Levenberg-Marquardt algorithm is used to train the network. The neural network is used to simulate the behaviour of the system. A multivariate regression model is also used for comparison with the results obtained by using the neural network model. The study results indicate that the neural network is able to give better predictions with less residual mean square error than those given by multivariate regression models.
ISSN:1364-8152