Time Series Forecasting of Hourly PM10 Using Localized Linear Models


The present paper discusses the application of localized linear models for the prediction of hourly PM10 concentration values. The advantages of the proposed approach lies in the clustering of the data based on a common property and the utilization of the target variable during this process, which enables the development of more coherent models. Two alternative localized linear modelling approaches are developed and compared against benchmark models, one in which data are clustered based on their spatial proximity on the embedding space and one novel approach in which grouped data are described by the same linear model. Since the target variable is unknown during the prediction stage, a complimentary pattern recognition approach is developed to account for this lack of information. The application of the developed approach on several PM10 data sets from the Greater Athens Area, Helsinki and London monitoring networks returned a significant reduction of the prediction error under all examined metrics against conventional forecasting schemes such as the linear regression and the neural networks.

Share and Cite:

A. Sfetsos and D. Vlachogiannis, "Time Series Forecasting of Hourly PM10 Using Localized Linear Models," Journal of Software Engineering and Applications, Vol. 3 No. 4, 2010, pp. 374-383. doi: 10.4236/jsea.2010.34042.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] K. Katsouyanni, “Ambient Air Pollution and Health,” British Medical Bulletin, Vol. 68, 2003, pp. 143-156.
[2] E. Samoli, A. Analitis, G. Touloumi, J. Schwartz, H. R. Anderson, J. Sunyer, L. Bisanti, D. Zmirou,. J. M. Vonk, J. Pekkanen,. P. Goodman,. A. Paldy,. C. Schindler and K. Katsouyanni, “Estimating the Exposure-Response Rela- tionships between Particulate Matter and Mortality within the APHEA Multicity Project,” Environmental Health Perspectives, Vol. 113, 2005, pp. 88-95.
[3] R. D. Morris, “Airborne Particulates and Hospital Admi- ssions for Cardiovascular Disease: A Quantitative Review of the Evidence,” Environmental Health Perspectives, Vol. 109, Supplement 4, 2001, pp. 495-500.
[4] E. G. Knox and E. A. Gilman, “Hazard Proximities of Childhood Cancer in Great Britain from 1953-1980,” Journal of Epidemiology and Health, Vol. 51, 1997, pp. 151-159.
[5] J. Kukkonen, L. Partanen, A. Karppinen, J. Ruuskanen, H. Junninen, M. Kolehmainen, H. Niska, S. Dorling, T. Chatterton, R. Foxall and G. Cawley, “Extensive Evaluation of Neural Extensive Evaluation of Neural Network Models for the Prediction of NO2 and PM10 Concentrations, Compared with a Deterministic Modell- ing System and Measurements in Central Helsinki,” Atmospheric Environment, Vol. 37, 2003, pp. 4539-4550.
[6] P. Perez, A. Trier and J. Reyes, “Prediction of PM2.5 Concentrations Several Hours in Advance Using Neural Networks in Santiago, Chile,” Atmospheric Environment, Vol. 34, 2000, pp. 1189-1196.
[7] M. W. Gardner, “The Advantages of Artificial Neural Network and Regression Tree Based Air Quality Models,” Ph.D. Dissertation, School of Environmental Sciences, University of East Anglia, Norwich, 1999.
[8] J. Hooyberghs, C. Mensink, G. Dumont, F. Fierens and O. Brasseur, “A Neural Network Forecast for Daily Average PM10 Concentrations in Belgium,” Atmospheric Environ- ment, Vol. 39, No. 18, 2005, pp. 3279-3289.
[9] J. B Ordieres, E. P. Vergara, R. S. Capuz and R. E. Salazar, “Neural Network Prediction Model for Fine Particulate Matter (PM2.5) on the US-Mexico Border in El Paso (Texas) and Ciudad Juαrez (Chihuahua),” Envi- ronmental Modelling & Software, Vol. 20, No. 5, 2005, pp. 547-559.
[10] G. Corani, “Air Quality Prediction in Milan: Feed- Forward Neural Networks, Pruned Neural Networks and Lazy Learning,” Ecological Modelling, Vol. 185, No. 2-4, 2005, pp. 513-529.
[11] C. Lin and C. Lee, “Neural Fuzzy Systems,” Prentice Hall, Upper Saddle River, 1996.
[12] M. Hagan and M. Menhaj, “Training Feed-Forward Networks with the Marquardt Algorithm”, IEEE Transac- tions on Neural Networks, Vol. 5, 1996, pp. 989-993.
[13] T. Chernichow, A. Piras, K. Imhof, P. Caire, Y. Jaccard, B. Dorizzi and A. Germond, “Short Term Electric Load Forecasting with Artificial Neural Networks,” Engine Intelligent Systems, Vol. 2, 1996, pp. 85-99.
[14] J. D Farmer and J. J. Sidorowich, “Predicting Chaotic Dynamics, Dynamic Patterns in Complex Systems,” In: J. A. S. Kelso, A. J. Mandell and M. F. Shlesinger, Ed., World Scientific, 1988, pp. 265-292.
[15] Y. Y. Hong and C. Y. Hsiao, “Locational Marginal Price Forecasting in Deregulated Electricity Markets Using Artificial Intelligence,” IEE Proceedings of Generation Transmission Distribution, Vol. 149, No. 5, 2002, pp. 621-626.
[16] J. Mitchell and S. Abe, “Fuzzy Clustering Networks: Design Criteria for Approximation and Prediction,” IEICE Transactions on Information and Systems, Vol. E79D, No. 1, 1996, pp. 63-71.
[17] A. B. Geva, “Hierarchical-Fuzzy Clustering of Temporal-Patterns and its Application for Time-Series Prediction,” Pattern Recognition Letters, Vol. 20, No. 14, 1999, pp. 1519-1532.
[18] M. Djukanovic, B. Babic, O. J. Sobajic and Y. H. Pao, “24-hour Load Forecasting,” IEE Proceedings – C, Vol. 140, 1993, pp. 311-318.
[19] J. B. McQueen, “Some Methods for Classification and Analysis of Multivariate Observations,” Proceedings of 5th Berkley Symposium on Mathematical Statistics and Probability, Berkeley, 27 December 1965-7 January 1966, pp. 281-297.
[20] D. J. Kim, Y. W. Park and D. J. Park, “A Novel Validity Index for Determination of the Optimal Number of Clus-ters,” IEICE Transactions on Information and Systems, Vol. E84-D, No. 2, 2001, pp. 281-285.

Copyright © 2021 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.