A Data Mining Application of Local Weather Forecast for Kayseri Erkilet Airport

Abstract

Data mining is a process used for the discovery of data correlation; the technique includes successful applications in the mass data field. Aeronautic meteorology is one of them. It includes the observation and forecast of meteorological events and parameters such as turbulence, rain, frost, fog, thunderstorm, etc. that affect flight operations. Aeronautic meteorology studies in the field of aviation. Understanding meteorological events is not possible without the observation of many parameters which are related to each other. Previous mass data should be overviewed for the future forecast. Expert opinions are also necessary in the process of analysis. At this point, data mining makes a great contribution to the analysis of mass data. This study aims at revealing the correlation between meteorological parameters that affect aviation and finding rules by classification. Forecasts were improved with relational analysis. As a result, reliable rules were identified that include estimation of fog, rain, snow, hail and thunderstorm events for Kayseri Erkilet Airport and these rules were analyzed in terms of their accuracy and reliability.

Keywords

• Data mining,aeronautical meteorology,classification,finding rules

References

1. [1] Hand D., Mannila H. and Smyth P., “Principles of data mining”, The Mit Press, England, (2001).
2. [2] Akpınar H., “Veri tabanlarında bilgi keşfi ve veri madenciliği”, İstanbul Üniversitesi İşletme Fakültesi Dergisi, 29: 1-22, (2000).
3. [3] Han J. and Kamber M., “Data mining: concepts and techniques”, Morgan Kaufmann Publishers, USA, (2001).
4. [4] Fayyad U., Piatetsky-Shapiro G. and Smyth P., “From data mining to knowledge discovery in databases”, American Association for Artificial Intelligence, 37-54, (1996).
5. [5] Özekes S., “Veri madenciliği modelleri ve uygulama alanları”, İstanbul Ticaret Üniversitesi Dergisi, 4: 65-82, (2003).
6. [6] Allen G. and LeMarchall J., “An evaluation of neural networks and discriminant analysis methods for application in operational rain forecasting”, Australian Meteorological Magazine, 43: 17-28, (1994).
7. [7] McGullagh J., Choi B. and Bluff K., “Genetic evolution of a neural networks input vector for meteorological estimations”, ICONIP’97, New Zealand 1046-1049, (1997).
8. [8] Stern H. and Parkyn K., “Predicting the likelihood of fog at Melbourne Airport”, 8th Conference on Aviation, Range and Aerospace Meteorology, American Meteorological Society, Dallas, 174-178, (1999).

9. [9] Mitsukura Y., Fukumi M. and Akamatsu N., “A design of genetic fog occurrence forecasting system by using LVQ network”, Proc. of IEEE SMC'2000, USA, 3678-3681, (2000).
10. [10] Trafalis T. B., Richman M. B. and A. White A., “Data mining techniques for improved WSR-88D rainfall estimation”, Computers & Industrial Engineering, 43: 775-786, (2002).
11. [11] Solomatine D. and Dulal K. N., “Model trees as an alternative to neural networks in rainfall—runoff modelling”, Hydrological Sciences Journal, 48: 399-411, (2003).
12. [12] Lee R. and Liu J., “iJADEWeatherMAN: A weather forecasting system using intelligent multiagent-based fuzzy neuro network”, IEEE Transactions On Systems, Man and Cybernetics – Part C: Applications and Reviews, 34: 369-377, (2004).
13. [13] Jareanpon C., Pensuwon W. and Frank R. J., “An adaptive RBF network optimised using a genetic algorithm applied to rainfall forecasting”, International Symposium on Communications and Information Technologies 2004 (ISCK 2004), 1005-1010, Japan, (2004).
14. [14] Suvichakorn A. and Tatnall A., “The application of cloud texture and motion derived from geostationary satellite images in rain estimation—A study on mid-latitude depressions”, Geoscience and Remote Sensing Symposium, 1682-1685, (2005).
15. [15] Banik S., Anwer M., Khan K., Rouf R. A. and Chanchary F. H., “Neural network and genetic algorithm approaches for forecasting Bangladeshi monsoon rainfall”, Proceedings of 11th International Conference on Computer and Information Technology (ICCIT 2008), Khulna-Bangladesh, 735-740, (2008).
16. [16] Pan X. and Wu J., “Bayesian neural network ensemble model based on partial least squares regression and its application in rainfall forecasting”, 2009 International Joint Conference on Computational Sciences and Optimization, Chine, 49-52, (2009).
17. [17] Aktaş C. and Erkuş O., “Lojistik regresyon analizi ile Eskişehir’in sis kestiriminin incelenmesi”, İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi, 16: 47-59, (2009).
18. [18] Bartok J., Habala O., Bednar P., Gazak M. and Hluchy L., “Data mining and integration for predicting significant meteorological phenomena”, Procedia Computer Science, 1: 37-46, (2010).
19. [19] Zazzaro G., Pisano F. M. and Mercogliano P., “Data mining to classify fog events by applying cost-sensitive classifier”, 2010 International Conference on Complex, Intelligent and Software Intensive Systems, Poland, (2010).
20. [20] Wu J., “An effective hybrid semi–parametric regression strategy for artificial neural network ensemble and its application rainfall forecasting”, 2011 Fourth International Joint Conference on Computational Sciences and Optimization, China, 1324-1328, (2011).
21. [21] Lee S. E. and Seo K. H., “The development of a statistical forecast model for Changma”, Weather and Forecasting, 28: 1304-1321, (2013).
22. [22] Agrawal R., Imielinski T. and Swami A., "Mining associations between sets of items in large databases", ACM SIGMOD Int'l Conf. on Management of Data, Washington D.C., 207-216, (1993).
23. [23] Giudici, P., “Applied data mining statistical methods for business and industry”, John Wiley&Sons Ltd., England, (2003).
24. [24] Baykal A. and Coşkun C., “Veri madenciliğinde sınıflandırma algoritmalarının bir örnek üzerinde karşılaştırılması”, Akademik Bilişim, Malatya, http://ab.org.tr/ab11/bildiri/67.pdf, (2011).