Natural Hazards and Earth System Science www.nat-hazards-earth-syst-sci.net 1561-8633 1684-9981 8 5 2008 10.5194/nhess-8-991-2008 http://www.nat-hazards-earth-syst-sci.net/8/991/2008/ http://www.nat-hazards-earth-syst-sci.net/8/991/2008/nhess-8-991-2008.html http://www.nat-hazards-earth-syst-sci.net/8/991/2008/nhess-8-991-2008.pdf 991 1000 2008-09-09 Risk assessment of atmospheric emissions using machine learning G. Cervone gcervone@gmu.edu P. Franzese Y. Ezber Z. Boybeyi College of Science, George Mason University, Fairfax, VA 22039, USA Eurasia Institute of Earth Sciences, Istanbul Technical University, Istanbul, 34469, Turkey Supervised and unsupervised machine learning algorithms are used to perform statistical and logical analysis of several transport and dispersion model runs which simulate emissions from a fixed source under different atmospheric conditions. <br><br> First, a clustering algorithm is used to automatically group the results of different transport and dispersion simulations according to specific cloud characteristics. Then, a symbolic classification algorithm is employed to find complex non-linear relationships between the meteorological input conditions and each cluster of clouds. The patterns discovered are provided in the form of probabilistic measures of contamination, thus suitable for result interpretation and dissemination. <br><br> The learned patterns can be used for quick assessment of the areas at risk and of the fate of potentially hazardous contaminants released in the atmosphere. Arya, P S.: Air pollution meteorology and dispersion, Oxford University Press, 1999. Beljaars, A. C M. and Holtslag, A. A M.: Flux parameterization over land surfaces for atmospheric models, J. Appl. Meteor., 30, 327–341, 1991. Bishop, C M.: Pattern Recognition and Machine Learning, Information Science and Statistics, Springer, New York, 2006. Boybeyi, Z., Ahmad, N N., Bacon, D P., Dunn, T J., Hall, M S., Lee, P. C S., Sarma, R A., and Wait, T R.: Evaluation of the Operational Multi-scale Environment model with Grid Adaptivity against the European Tracer Experiment, J. Appl. Meteor., 40, 1541–1558, 2001. Cervone, G., Panait, L., and Michalski, R.: The development of the AQ20 learning system and initial experiments, in: Tenth International Symposium on Intelligent Information Systems, Zakopane, Poland, 2001. Gardner, M W. and Dorling, S R.: Artificial neural networks (the multilayer perceptron) – a review of applications in the atmospheric sciences – application for wind retrieval from spaceborne scatterometer data, Atmos. Environ., 32, 2627–2636, 1998. Goldberg, D E.: Genetic algorithms and rule learning in dynamic system control, in Proc of the International Conference on Genetic Algorithms and Their Applications, 8–15, Pittsburgh, PA, 1985. Hanna, S R.: A review of atmospheric diffusion models for regulatory applications, Tech. Rep. 177, World Meteorological Organization, Geneva, 1982. Hartigan, J A. and Wong, M.: A K-means clustering algorithm, Appl. Stat., 28, 100–108, 1979. Hastie, T. and Tibshirani, R.: Generalized additive models, Stat. Sci., 1, 297–310, 1986. Langley, P.: Elements of Machine Learning, Morgan Kaufmann Publishers, Inc., San Francisco, California, 1996. Lin, Y.-L., Farley, R D., and Orville, H D.: Bulk parameterization of the snow field in a cloud model, J. Clim. Appl. Meteorol., 22, 1065–1092, 1983. Lloyd, S P.: Least squares quantization in pcm, IEEE Transactions on Information Theory, 28, 128–137, 1982. MacQueen, J B.: Some methods for classification and analysis of multivariate observations, in: Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, vol 1, 281–297, University of California Press, 1967. Mahrer, Y. and Pielke, R A.: The effects of topography on the sea and land breezes in a two-dimensional numerical model, Mon. Weather Rev., 105, 1151–1162, 1977. Marzban, C.: A neural network for tornado prediction based on doppler radar-derived attributes, J. Appl. Meteorol., 35, 617–626, 1995. Marzban, C.: A neural network for damaging wind prediction, Weather Forecast., 16, 600–610, 1997. Marzban, C.: Scalar measures of performance in rare-event situations, Weather Forecast., 13, 753–763, 1998. Mellor, G L. and Yamada, T.: A hierarchy of turbulence closure models for planetary boundary layers, J. Atmos. Sci., 31, 1781–1806, 1974. Mitchell, T.: Machine Learning, McGraw-Hill Education (ISE Editions), 1997. Montero, G., Rodriguez, E., Montenegro, R., Escobar, J M., and Gonzalez-Yuste, J M.: Genetic algorithms for an improved parameter estimation with local refinement of tetrahedral meshes in a wind model, Adv. Eng. Softw., 36, 3–10, 2005. Noilhan, J. and Planton, S.: A simple parameterization of land surface processes for meteorological models, Mon. Weather Rev., 117, 536–549, 1998. Pasquill, F.: Atmospheric Diffusion, D. Van Nostrand Company LTD, 1962. Quinlan, R J.: C4.5: Programs for Machine Learning, Morgan Kaufmann Series in Machine Learning, Morgan Kaufmann, 1993. Roberts, O.: The theoretical scattering of smoke in a turbulent atmosphere, Proc. Roy. Soc. Lond. Ser.-A, 104, 640–654, 1923. Shapiro, S C. (Ed.): Encyclopedia of Artificial Intelligence, John Wiley and Sons, 1987. Smolarkiewicz, P K.: A fully multidimensional positive definite advection transport algorithm with small implicit diffusion, J. Comput. Phys., 54, 325–362, 1984. Sutton, O G.: A theory of eddy diffusion in the atmosphere, Proc. Roy. Soc. Lond. Ser.-A, 135, 143–165, 1932. Taylor, G I.: Diffusion by continuous movements, Proc. Lond. Math. Soc., 20, 196–211, 1921. Hsieh, W. W.: An adaptive nonlinear mos scheme for precipitation forecasts using neural networks, Weather Forecast., 18, 303–310, 2003.