Drought Estimation of Çanakkale with Data Mining

Abstract

Drought estimation is important considering the harmful effects of the climate change in recent years. In this study, various models are developed with data mining technique for the drought estimation of Çanakkale, Turkey. Standardized precipitation index (SPI) values for 3, 6, 9, 12 and 24 months are calculated using the precipitation data of Çanakkale, Gökçeada and Bozcaada stations. The calculated SPI values of Gökçeada and Bozcaada are used as input parameters in developing data mining models with different algorithms. Examining the model results, it is observed that data mining technique is effective in drought estimation. 

Keywords

• Drought,Data mining,SPI,Çanakkale,Turkey

Veri Madenciliği ile Çanakkale İli Kuraklık Tahmini

Abstract

Son yıllardaki iklim değişikliğinin zararlı etkileri göz önüne alındığında kuraklık tahmini oldukça önemlidir. Bu çalışmada, Çanakkale iline ait kuraklık tahmini için veri madenciliği ile modeller geliştirilmiştir. Çanakkale, Gökçeada ve Bozcaada yağış istasyonlarına ait yağış verileri ile 3, 6, 9, 12 ve 24 aylık standart yağış indeksi (SYİ) değerleri hesaplanmıştır. Hesaplanan Gökçeada ve Bozcaada’nın SYİ değerleri veri madenciliği modellerinde girdi olarak kullanılmıştır ve farklı algoritmalar ile modeller geliştirilmiştir. Model sonuçları, hesaplanan SYİ değerleri ile karşılaştırıldığında, veri madenciliği yönteminin kuraklık tahmininde iyi sonuçlar verdiği gözlemlemiştir.

Keywords

• Çanakkale,Kuraklık,Veri madenciliği,SYİ,Türkiye

References

1. [1] S. Sırdaş and Z. Şen, “Meteorological drought modelling and application to Turkey,” Itu Journal/D Engineering, vol. 2, no.2, pp. 95-103, 2003.
2. [2] P. Dahal, N. S. Shrestha, M. L. Shrestha, N. Y. Krakauer, J. Panthi, S. M. Pradhanang, A. Jha and T. Lakhankar, “Drought risk assessment in central Nepal: temporal and spatial analysis,” Natural Hazards, vol. 80, no. 3, pp. 1913-1932, 2016.
3. [3] M. Gocic and S. Trajkovic, “Spatiotemporal characteristics of drought in Serbia,” Journal of Hydrology, vol. 510, pp.110-123, 2014.
4. [4] H.Vathsala and S.G. Koolagudi, “Prediction model for peninsular Indian summer monsoon rainfall using data mining and statistical approaches,” Computers and Geosciences, vol. 98, pp. 55-63, 2017.
5. [5] Ö. Terzi, E. D. Taylan, O. Özcanoğlu and T. Baykal, “A Wavelet-ANFIS Hybrid model for drought forecasting,” 8th International Advanced Technologies Symposium, Elazığ, Turkey, 2017, pp. 3251-3258.
6. [6] S. P. Norman, F. H. Koch and W. W. Hargrove, “Review of broad-scale drought monitoring of forests: Toward an integrated data mining approach,” Forest Ecology and Management, vol. 380, pp. 346-358, 2016.
7. [7] H. A. Afan, A. El-shafie, W. H. M. W Mohtar and Z. M.Yaseen, “Past, present and prospect of an Artificial Intelligence (AI) based model for sediment transport prediction,” Journal of Hydrology, vol. 541, pp. 902-913, 2016.
8. [8] M. Zounemat-Kermani, Ö. Kişi, J. Adamowski and A. Ramezani-Charmahineh, “Evaluation of data driven models for river suspended sediment concentration modeling,” Journal of Hydrology, vol. 535, pp. 457-472, 2016.

9. [9] V. Nourani, A.H. Baghanam, J. Adamowski and Ö. Kisi, “Applications of hybrid wavelet– artificial intelligence models in hydrology: A review,” Journal of Hydrology, vol. 514, pp. 358-377, 2014.
10. [10] Ö. Terzi, “Veri madenciliği süreci kullanilarak yağiş tahmini,” Akıllı Sistemlerde Yenilikler ve Uygulamaları Sempozyumu, Trabzon, Turkey, 2012, ss. 126-129.
11. [11] A. Jalalkamali, M. Moradi and N. Moradi, “Application of several artificial intelligence models and ARIMAX model for forecasting drought using the Standardized Precipitation Index,” International Journal of Environmental Science and Technology, vol. 12, no. 4, pp. 1201-1210, 2015.
12. [12] T. Tadesse, D. A. Wilhite, S. K. Harms, M. J. Hayes and S. Goddard, “Drought monitoring using data mining techniques: A case study for Nebraska, USA,” Natural Hazards, vol. 33, no. 1, pp. 137-159, 2004.
13. [13] B. Choubin, A. Malekian, and M. Golshan, “Application of several data-driven techniques to predict a standardized precipitation index.” Atmósfera, vol. 29, no. 2, pp. 121-128, 2016.
14. [14] R. C. Deo and M. Şahin, “Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydrometeorological parameters and climate indices in eastern Australia,” Atmospheric Research, vol. 161, pp. 65-81, 2015.
15. [15] C. L. Wu, K. W. Chau and Y. S. Li, “Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques,” Water Resources Research, vol. 45, no. 8, 2009.
16. [16] Ö.Terzi and T. Baykal, “Data mining process for river suspended sediment estimation,” SDU International Journal of Technological Science, vol. 8, no 3, pp. 19-26, 2016.
17. [17] T. B McKee, N. J. Doesken and J. Kleist, “The relationship of drought frequency and duration to time scales,” Eighth Conference on Applied Climatology, American Meteorological Society, Anaheim, CA, 1993, pp. 1-6.
18. [18] D. C. Edwards and T. B. McKee, “Characteristics of 20th century drought in the united states at multiple time scales,” Atmospheric Science Paper, vol. 634, pp. 1-30, 1997.
19. [19] K. T. Redmond, “Integrated climate monitoring for drought detection,” Drought: A Global Assessment, edited by Wilhite, DA, Routledge, London, 2000.
20. [20] D. Atmaca , “Regional drought analysis on Konya province by using standardized precipitation index (SPI),” M.S. Thesis, Department of Agricultural Structures and Irrigation, Gaziosmanpaşa University, Tokat, Turkey, 2011.
21. [21] WMO, “Standardized Precipitation Index User Guide,” WMO-No. 1090, World Meteorological Organization, 2012.
22. [22] H. Edelstein, (1997). [Online] Available: http://wwww.db2mag.com/db_area/archives/19
23. [23] J. Han and M. Kamber, Data mining: concepts and techniques, 3rd ed., New York, USA: Elsevier, 2006, pp. 770.
24. [24] S. T. Li and L. Y. Shue, “Data mining to aid policy making in air pollution management,” Expert System and Applications, vol. 27, pp. 331-340, 2004.
25. [25] Z. H. Zhou, “Three Perspectives of Data Mining”, Artificial Intelligence, vol. 143, no.1, pp. 139–146, 2003.
26. [26] R. Mattison, Data Warehousing: Strategies, Technologies and Techniques Statistical Analysis, SPSS Inc. WhitePapers, 1996.
27. [27] T. K. Ho, “The random subspace method for constructing decision forests”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 832-844, 1998.
28. [28] J. G. Cleary, L.E. Trigg, “K* an instance-based learner using an entropic distance measure”, In: 12th International Conference on Machine Learning, 1995, pp. 108-114.
29. [29] B. Jason, (2016, July 27). [Online]. Available: https://machinelearningmastery.com/useensemble-machine-learning-algorithms-weka/
30. [30] P. J. Rousseeuw and M.L. Annick, Robust regression and outlier detection, 1st ed., vol. 589. New Jersey, USA: John Wiley & Sons, 2005.
31. [31] Çanakkale Municipality. (2018, Feb 10). [Online]. Available: http://www.canakkale.bel.tr/ icerik/1941/cografi-yapi
32. [32] İzmir Meteorology Directorate. (2018, Feb 10). [Online]. Available: http://izmir.mgm.gov.tr/ FILES/iklim/canakkale_iklim.pdf