Abstract
Air quality has become a major issue during the last decades for a great number of cities and a matter of concern for both citizens and scientists. The quality of life has deteriorated in urban regions due to high pollution levels and a large number of people suffer from pollution effects on health. The prediction of air pollution episodes is very useful in that it enables the local authorities to give a warning against high pollutant concentrations or to take limitation measures on the emission sources. hi the past, efforts for pollution level forecasting have been reported using mathematical models (simulating the physical process) or statistical methods (Zannetti, 1990). The mathematical model operation requires high computational capacity, meteorological data and emission inventory. The required meteorological data are very difficult to collect and process, while the creation of an emission inventory is not an easy task.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Amanatidis, G. T., 1992, Sulphate, sulphur dioxide and rainfall relationships in the Athens basin, Greece, Fresenius Environmental Bulletin 1:462.
Duda, R. O., and Hart, P. E., 1973, “Pattern Classification and Scene Analysis,” Wiley, New York.
Fahlman, S. E., 1988, Faster learning variations on back propagation: an empirical study, in “Proceedings of the 1988 Conmectionist Models Summer School,” San Mateo, 38.
Finzi, G., and Tebaldi, G., 1982, A mathematical model for air pollution forecast and alarm in an urban area, Atmospheric Environment 16(9):2055.
Fogelman Soulie, F., (1991), Neural network architectures and algorithms: a perspective, in “Artificial Neural Networks,” T. Kohonen, K. Makisara, O. Simula, and J. Kangas, eds., Elsevier.
Fimahashi, K-I., 1989, On the approximate realization of continuous mappings by neural networks, Neural Networks 2:183.
Gatos, V., Karras, D. A., and Perantonis, S. J., Optical character recognition using novel feature extraction and neural networks classification techniques, in “Proceedings of the Workshop on Neural Networks: Techniques and Applications” Liverpool, UK.
Inoue, T., Tagauri, M., and Hoshi, M., 1986, Prediction of nitrogen oxide concentration by a regression model, Atmospheric Environment 20:2325.
Karras, D. A., and Perantonis, S. J., 1993, Efficient constrained training algorithms for feedforward networks, IEEE Trans. on Neural Networks, under review.
Karras, D. A. and Perantonis, S. J., 1993, Comparison of learning algorithms for feedforward networks in large scale networks and problems, in “Proceedings of the International Joint Conference on Neural Networks,” Nagoya, Japan.
Kohonen, T., 1989, “Self-Organization and Associative Memory,” Springer-Verlag, BerlinHeidelberg-New York-Tokyo.
Kohonen, T., 1990, Improved versions of learning vector quantization, in “Proceedings of the International Joint Conference on Neural Networks,” San Diego, 1:545.
Kohonen, T., Kangas, J., Laaksonen, J. and Torkkola, K., 1992, LVQ-PAK: the learning vector quantization program package, Version 2.0.
Paliatsos, A. G. and Amanatidis, G. T., 1993, Smoke concentrations in Athens, Greece: trends and strong episodes, The Science of the Total Environment, in press.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J., 1986, Learning internal representations by error propagation, in “Parallel Distributed Processing: Explorations in the Microstructure of Cognition,” D. E. Rumelhart and J. L. McClelland, eds., MIT Press, Cambridge, MA.
Siriopoulos, C., Karakoulas, G., Doukidis, G., Perantonis, S. and Varoufakis, S., 1992, Applications of neural networks and knowledge-based systems in stock investment management: a comparison of performances, Neural Network World 2(6):785.
Weigend, A. S., Rumelhart, D. E. and Huberman, B. A., 1991, Generalization by weight elimination with application to forecasting, in “Advances in Neural Information Processing Systems,” 875.
Zannetti, P., 1990, “Air Pollution Modeling,” Computational Mechanics Publ., New York.
Zerefos, C. S., Bais, A., Ziomas, I., Paliatsos, A. G., Amanatidis, G. T., and Tourpali, K., 1989, Review of air pollution trends in Greece, in “Proceedings of the Technical Conference on the Monitoring and Assessment of Changing Composition of the Troposphere,” Sofia, Bulgaria; WMO 724: 47.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer Science+Business Media New York
About this chapter
Cite this chapter
Perantonis, S.J., Vassilas, N., Amanatidis, G.T., Varoufakis, S.J., Bartzis, J.G. (1994). Neural Network Techniques for SO2 Episode Prediction. In: Gryning, SE., Millán, M.M. (eds) Air Pollution Modeling and Its Application X. NATO · Challenges of Modern Society, vol 18. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-1817-4_34
Download citation
DOI: https://doi.org/10.1007/978-1-4615-1817-4_34
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5734-6
Online ISBN: 978-1-4615-1817-4
eBook Packages: Springer Book Archive