10.2190/2X6W-R4M5-HX0E-T7TP 2X6WR4M5HX0ET7TP 191 AIR QUALITY PREDICTION: AN OPPORTUNISTIC NEURO-ENSEMBLE APPROACH 191 205 20060331 20060331 20060331 20060331 2X6WR4M5HX0ET7TP.pdf http://baywood.metapress.com/link.asp?target=contribution&id=2X6WR4M5HX0ET7TP 3 A. K. DIKSHIT S. V. BARAI SAMEER SHARMA Indian Institute of Technology Bombay, India Indian Institute of Technology Kharagpur, India Tata Consulting Engineers Ltd., New Delhi, India The present article discusses the development of neural-network-based air quality prediction models which can work with a limited number of data sets and are robust enough to handle data with noise. Five different variations of neural network models (partial recurrent network (PRNM), sequential network construction (SNCM), self-organizing feature maps (SOFM), moving window (MWM), and integrated normalized autoregressive moving average-self-organized feature maps models (NARMA-SOFM)), were implemented in a WINDOWS environment using MATLAB software. Developed models were run to simulate and forecast the daily average data for three parameters: RPM (respirable particulate matter), SO<SUB>2</SUB> (sulphur dioxide), and NO<SUB>2</SUB> (nitrogen dioxide) for the Ashram Chowk location in New Delhi, India. The implemented models were found to predict air quality patterns with modest accuracy. To improve the models' performance, an innovative approach using an opportunistic ensemble of the first four developed neural network models (OEM) was proposed for predicting the same short-term data. The ensemble approach indeed demonstrated an improvement on earlier models. However, the NARMA-SOFM model performed the best. S. Sharma, A. K. Dikshit, and S. V. Barai, Studies on Neural Networks Based Air Quality Predictors, International Journal of Environment and Pollution, 19:5, pp. 1-12, 2003. F. Giorgio and M. Piero, Mathematical Models for Planning and Controlling Air Quality, Proceedings of an October 1979 IIASA Workshop, Pergamon Press, 1982. R. P. Lippman, An Introduction to Computing with Neural Nets, IEEE ASSP Magazine, pp. 6-22, April 1987. J. E. Dayoff, Neural Networks Architecture: An Introduction, Van Nostrand Reinhold, New York, 1990. S. Haykin, Neural Networks: A Comprehensive Foundation (2nd Edition), Pearson Education Asia, Addison Wesely Longman, Delhi, 2000. J. Principe and J. M. Kuo, Dynamic Modeling of Chaotic Time Series with Neural Networks, Proceedings of Neural Information Processing Systems, NIPS' 1994, Volume 7, pp. 311-318, MIT Press, Massachusetts, 1995. M. Boznar, M. Lesjak, and P. Mlakar, A Neural Network-Based Method for Short Term Prediction of Ambient SO Concentrations in Highly Polluted Industrial Areas of Complex Terrain, Atmosphere and Environment, 27B, pp. 221-230, 1993. A. Basheer and M. Najjar, Predicting Dynamic Response of Adsorption Columns with Neural Nets, Journal of Computing in Civil Engineering, ASCE, 10:1, pp. 211-220, 1996. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology, Artificial Neural Networks in Hydrology. I: Preliminary Concepts, Journal of Hydrologic Engineering, ASCE, 5:2, pp. 115-123, 2000. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology, Artificial Neural Networks in Hydrology. II: Preliminary Concepts, Journal of Hydrologic Engineering, ASCE, 5:2, pp. 124-137, 2000. L. Hadjiiski and P. Hopke, Application of Artificial Neural Networks to Modeling and Prediction of Ambient Ozone Concentrations, Journal of Air and Waste Management Association, 50, pp. 894-901, 2000. K. Thirumalaiah and M. C. Deo, River Stage Forecasting Using Artificial Neural Networks, Journal of Hydrologic Engineering, ASCE, 3:1, pp. 26-32, 1998. K. Thirumalaiah and M. C. Deo, Hydrological Forecasting Using Neural Networks, Journal of Hydrologic Engineering, ASCE, 5:2, pp. 180-189, 2000. S. V. Barai and Y. Reich, Ensemble Modeling or Selecting the Best Model: Many Could be Better than One, Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 13, pp. 377-386, 1999. Math Works, MATLAB User's Guide, Math Works Inc., Massachusetts, 2000. H. Demuth and M. Beale, Neural Networks Toolbox Manual, Math Works Inc., Massachusetts, 1992. J. T. Connor, R. D. Martin, and L. E. Atlas, Recurrent Neural Networks and Robust Time Series Prediction, IEEE Trans. Neural Networks, 5:2, pp. 240-253, 1994. A. G. Parlos, O. T. Rais, and A. F. Atiya, Multi-Step-Ahead Prediction Using Dynamic Recurrent Neural Networks, Neural Networks, 13, pp. 765-786, 2000. A. D. Back and A. C. Tsoi, FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling, Neural Computation, 3, pp. 375-385, 1991. J. C. Tomasz and J. M. Zurada, Sequential Network Construction for Time Series Predictions, in Proceedings of the IEEE International Joint Conference on Neural Networks, Houston, Texas, pp. 2034-2039, June 9-12, 1977. T. Kohonen, The Self-Organizing Map, Proceedings of the IEEE, 78, pp. 1464-1480, 1990. S. Sharma, Neuro Air Quality Predictors, M.Tech. thesis, Department of Civil Engineering, IIT Kharagpur, 2002.