ANN-based PM prediction model for assessing the temporal variability of PM10, PM2.5 and PM1 concentrations at an urban roadway
by B. Srimuruganandam; S.M. Shiva Nagendra
International Journal of Environmental Engineering (IJEE), Vol. 7, No. 1, 2015

Abstract: In this paper, hourly particulate matter (PM10, PM2.5 and PM1) concentrations, traffic and meteorological parameters monitored at urban roadway in India during November 2007-May 2009 are used to develop 1-hr and 24-hr average artificial neural network (ANN)-based PM prediction models. Maximum of eight meteorological and five traffic characteristic variables have been used in the models' formulation. Three scenarios were considered - considering both meteorological and traffic characteristics as input parameters; only meteorological inputs; and only traffic characteristics input data. The performance of all the developed models are evaluated on the basis of index of agreement (IA) and other statistical parameters, viz. the mean and the deviations of the observed and predicted concentrations, mean bias error, mean square error, systematic and unsystematic root mean square error, coefficient of determination and linear best fit constant and gradient. The performance of 24-hr average ANN-based PM model (ANNDMT) showed good performance (IA > 0.85 i.e. more than 85% of the predictions are error free) on the validation dataset. While, the 1-hr average ANN-based PM model (ANNHMT) showed reasonable performance (IA < 0.75) on the validation dataset. This study demonstrates that ANN is capable of modelling complex PM dispersion phenomenon at urban roads having heterogeneous traffic.

Online publication date: Wed, 06-May-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Environmental Engineering (IJEE):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com