Potential Assessment of Neural Network and Decision Tree Algorithms for Forecasting Ambient and CO Concentrations: Case Study
This article has a reply.
VIEW THE REPLYThis article has a reply.
VIEW THE REPLYPublication: Journal of Hazardous, Toxic, and Radioactive Waste
Volume 20, Issue 4
Abstract
Air pollution in megacities have caught attention of both researchers and policymakers because of increasing emissions, poor air quality, and potential adverse health impacts on densely inhabited populations. Oxides of nitrogen, particulate matter, carbon monoxide, and hydrocarbons are the major air pollutants of vehicular emissions near major intersections and arterials in megacities. The present study is mainly aimed at predicting and CO concentrations at an income tax office (ITO) intersection in the megacity of Delhi. Artificial neural networks (ANNs) and decision tree algorithms (e.g., REPTree and M5P algorithm techniques) are used to predict hourly fine particulate matter () and carbon monoxide (CO) pollutant concentrations at the ITO intersection. Factors and parameters, such as meteorological conditions, traffic, and vehicular emissions, that affect pollutant concentrations are used in different combinations for the model development. Performance evaluation of ANN, REPTree, and M5P algorithms for hourly and CO concentration prediction is carried out, and the effects of the aforementioned factors are discussed. The M5P algorithm performs better than ANN and REPTree algorithms in that it precisely captures the relationships among the predictor variables and pollutant concentrations.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
We are grateful to the Central Pollution Control Board, Central Road Research Institute, and Transport Department, New Delhi, for making the relevant data freely available. We also thank the Indian Meteorological Department for providing the necessary data as per the norms.
References
Automotive Research Association of India. (2007). “Air quality monitoring project-Indian clean air programme (ICAP).”, Pune, India.
Biswas, J., Upadhyay, E., Nayak, M., and Yadav, A. K. (2011). “An analysis of ambient air quality conditions over Delhi, India from 2004 to 2009.” Atmos. Clim. Sci., 1(4), 214–221.
Boznar, M., Lesjak, M., and Mlakar, P. (1993). “A neural network based method for the short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain.” Atmos. Environ., 27(2), 221–230.
Breiman, L., Freidman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classifcation and regression trees, Wadsworth and Brooks-Cole, Belmont, CA.
Burney, S. M. A., Jilani, T. A., and Ardil, C. (2008). “Levenberg-Marquardt algorithm for Karachi stock exchange share rates forecasting.” World Acad. Sci. Eng. Technol., 2(4), 171–176.
Cai, M., Yin, Y., and Xie, M. (2009). “Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach.” Transp. Res. Part D, 14(1), 32–41.
CDP Delhi (City Development Plan Delhi). (2006). “Review of road network and transport system.” Dept. of Urban Development, Government of Delhi, New Delhi, India.
CRRI (Central Road Research Institute). (1998). Evaluation of emission characteristics and compliance of emission standards for in-use petrol driven vehicles and critical appraisal of the efficacy of the existing pollution checking system in Delhi, Environment and Road Traffic Safety Div., New Delhi, India.
Daud, M. N. R., and Corne, D. W. (2007). “Human readable rule inductionin medical data mining: A survey of existing algorithms.” Proc., World Scientific and Engineering Academy and Society (WSEAS) European Computing Conf., Vol. 1, Springer, Athens, Greece, 787–798.
Elkamel, A., Abdul-Wahab, S., Bouhamra, W., and Alper, E. (2001). “Measurement and prediction of ozone levels around a heavily industrialized area: A neural network approach.” Adv. Environ. Res., 5(1), 47–59.
Esplin, G. L. (1995). “Approximate explicit solution to the general line source problem.” Atmos. Environ., 29(12), 1459–1463.
Gardner, M. W., and Dorling, S. R. (1998). “Artificial neural networks: The multilayer perceptron: A review of applications in atmospheric sciences.” Atmos. Environ., 32(14–15), 2627–2636.
Gardner, M. W., and Dorling, S. R. (1999). “Neural network modelling and prediction of hourly NOx and concentrations in urban air in London.” Atmos. Environ., 33(5), 709–719.
Gardner, M. W., and Dorling, S. R. (2000). “Statistical surface ozone models: An improved methodology to account for non-linear behaviour.” Atmos. Environ., 34(1), 21–34.
Gokhale, S., and Khare, M. (2005). “A hybrid model for predicting carbon monoxide from vehicular exhausts in urban environments.” Atmos. Environ., 39(22), 4025–4040.
Gokhale, S., and Pandian, S. (2007). “A semi-empirical box modeling approach for predicting thecarbon monoxide concentrations at an urban traffic intersection.” Atmos. Environ., 41(36), 7940–7950.
Goyal, M. K., and Ojha, C. S. P. (2011). “Estimation of scour downstream of a ski-jump bucket using support vector and M5 model tree.” Water Resour. Manage., 25(9), 2177–2195.
Guttikunda, S. K., and Calori, G. (2013). “A GIS based emissions inventory at 1 km x 1 km spatial resolution for air pollution analysis in Delhi, India.” Atmos. Environ., 67, 101–111.
Hagan, M. T., and Menhaj, M. B. (1994). “Training feed forward networks with the Marquardt algorithm.” IEEE Trans. Neural Networks, 5(6), 989–993.
Hall, P., and Miller, H. (2009). “Using generalized correlation to effect var-iable selection in very high dimensional problems.” J. Comput. Graph. Stat., 18(3), 533–550.
Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., and Brasseur, O. (2005). “A neural network forecast for daily average concentrations in Belgium.” Atmos. Environ., 39(18), 3279–3289.
Hsu, K.-L., Gupta, H. V., and Sorooshian, S. (1995). “Artificial neural network modeling of the rainfall-runoff process.” Water Resour. Res., 31(10), 2517–2530.
Kukkonen, J., et al. (2003). “Extensive evaluation of neural network models for the prediction of and concentrations, compared with a deterministic modelling system and measurements in central Helsinki.” Atmos. Environ., 37(32), 4539–4550.
Lim, T. S., Loh, W. Y., and Shih, Y. S. (1997). An empirical comparison of decision trees and other classification methods, Dept. of Statistics., Univ. of Wisconsin, Madison, WI.
Milionis, A. E., and Davis, T. D. (1994). “Regression and stochastic models for air pollution: Part I: Review comments and suggestions.” Atmos. Environ., 28(17), 2801–2810.
Ministry of Environment and Forests. (1997). “White paper on air pollution on Delhi with an action plan.” Delhi, India.
Moseholm, L., Silva, J., and Larson, T. C. (1996). “Forecasting carbon monoxide concentration near a sheltered intersection using video traffic surveillance and neural networks.” Transp. Res. Part D., 1(1), 15–28.
Nagendra, S. M. S., and Khare, M. (2004). “Artificial neural network based line source models for vehicular exhaust emission predictions ofan urban roadway.” J. Transp. Res. Part D, 9(3), 199–208.
Nagendra, S. M. S., and Khare, M. (2006). “Artificial neural network approach for modelling nitrogen dioxide dispersion from vehicular exhaust emissions.” Ecol. Modell., 190(1-2), 99–115.
Nash, J. E., and Sutcliffe, J. V. (1970). “River flow forecasting through conceptual models: 1. A discussion of principles.” J. Hydrol. (Amsterdam), 10(3), 282–290.
Pandey, J. S., Rakesh, K., and Devotta, S. (2005). “Health risks of , SPM and in Delhi (India).” Atmos. Environ., 39(36), 6868–6874.
Perez, P., and Trier, A. (2001). “Prediction of NO and concentrations near a street with heavy traffic in Santiago, Chile.” Atmos. Environ., 35(10), 1783–1789.
Pires, J. C. M., et al. (2012). “Optimization of artificial neural network models through genetic algorithms for surface ozone concentration forecasting.” Environ. Sci. Pollut. Res., 19(8), 3228–3234.
Quinlan, J. R. (1992). “Learning with continuous classes.” Proc., 5th Australian Joint Conf. on Artificial Intelligence, World Scientific, Singapore, 343–348.
Rege, M. A., and Tock, R. W. (1996). “A simple neural network for esti-mating emission rates of hydrogen sulphide and ammonia from single point source.” J. Air Waste Manage. Assoc., 46(10), 953–962.
Schnelle, K. B., and Dey, P. R. (2000). Atmospheric dispersion modelling compliance guide, McGraw-Hill, New York.
Senthilkumar, A. R., Ojha, C. S. P., Goyal, M. K., Singh, R. D., and Swamee, P. K. (2012). “Modelling of suspended sediment concentration at Kasol in India using ANN, fuzzy logic and decision tree algorithms.” J. Hydrol. Eng., 394–404.
Srivastava, K., and Jain, V. K. (2008). “A study to characterize the influence of outdoor SPM and metals on indoor environments in Delhi.” J. Environ. Sci. Eng., 47(3), 222–231.
ToI. (2014). “Delhi is world’s 2nd most populous city, UN report.” The Times of India, Jul. 12, 15.
Varshney, K., and Padhy, P. K. (1998). “Total volatile organic compounds in urban environment of Delhi.” J. Air Waste Manage. Assoc., 48(5), 448–453.
Viotti, P., Liuti, G., and Genova, P. D. (2002). “Atmospheric urban pollution: Applications of an artificial neural network (ANN) to the city of Perugia.” Ecol. Modell., 148(1), 27–46.
Witten, I. H., and Frank, E. (2005). Data mining: Practical machine learning tools and techniques, 2nd Ed., Morgan Kaufmann, San Francisco.
Information & Authors
Information
Published In
Journal of Hazardous, Toxic, and Radioactive Waste
Volume 20 • Issue 4 • October 2016
Copyright
© 2015 American Society of Civil Engineers.
History
Received: Aug 4, 2014
Accepted: Feb 2, 2015
Published online: Apr 2, 2015
Discussion open until: Sep 2, 2015
Published in print: Oct 1, 2016
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.