Clustering of Precipitation in the Black Sea Region with by Fuzzy C-Means and Silhouette Index Analysis

Abstract

In recent years, there has been a noticeable increase in the number of disasters caused by the effects of global climate change. In this context, various studies are carried out in our country and in the world in order to reduce the effects of climate change. The classification of regions affected by climate change into similar classes in terms of climate parameters is important in terms of applying similar methods in studies to be carried out in these regions. Thus, a correct strategy will be determined in the studies to be carried out in order to reduce the effects of climate change. The observation records evaluated within the scope of the study were used from 31 stations in the Black Sea Region of the Turkish State Meteorological Service, covering the period between 1982 and 2020. Cluster analysis was carried out using the Fuzzy C-Means. As a result of the study, the optimum cluster among the clusters formed by Fuzzy C-Means was determined by Silhouette index analysis. The optimal number of clusters is suggested as 4.

Keywords

• Fuzzy C-Means
• Clustering
• Silhouette analysis
• Precipitation

References

1. Bezdek JC, Ehrlich R, Full W. 1984. FCM: The fuzzy C-means clustering algorithm. Comput Geosci, 10(2-3): 191-203. DOI: 10.1016/0098-3004(84)90020-7.
2. Bezdek JC. 1980. A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Transact Pattern Analysis Machine Intel, 2(1): 1-8. DOI: 10.1109/TPAMI.1980.4766964.
3. Çelik İH, Usta G, Yilmaz G, Usta M. 2020. An assessment on the technological disasters experienced in Turkey (between the years of 2000-2020). Artvin Coruh Univ Int J Soc Sci, 6(2): 49-57. DOI: 10.22466/acusbd.776580.
4. Çıtakoğlu H, Demir V, Haktanır T. 2017. L−momentler yöntemiyle Karadeniz’e dökülen akarsulara ait yillik anlik maksimum akim değerlerinin bölgesel frekans analizi. Niğde Ömer Halisdemir Üniv Müh Bil Derg, 6(2): 571-580. DOI: 10.28948/ngumuh.341711.
5. Demircan M, Arabacı H, Coşkun M, Türkoğlu N, Çiçek İ. 2017. İklim değişikliği ve halk takvimi: Maksimum sıcaklık desenleri ve değişimi. IV. Türkiye İklim Değişikliği Kongresi, July 5-7, 2017, İstanbul, Türkiye, pp: 11.
6. Dikbas F, Firat M, Koc AC, Gungor M. 2012. Classication of precipitation series using fuzzy cluster method. Int J Climatol, 32(10): 1596-1603. DOI: 10.1002/joc.2350.
7. Erinç S. 1949. The climates of Turkey according to Thornthwaite’s classifications. Ann Assoc Am Geograp, 39: 26-46. DOI: 10.2307/2561098.
8. Fırat M, Dikbaş F, Koç AC, Güngör M. 2012. Classification of annual precipitations and identification of homogeneous regions using k-means Method. Tech J, 23(113): 6037-6050.

9. Günay Atbaş AC. 2008. A study on determining the number of clusters in cluster analysis. MSc Thesis, Ankara University, Graduate School of Natural and Applied Sciences, Ankara, Türkiye, pp: 68.
10. Gundüz F. 2022. Lessons learned from the perspective of women and gender in disasters, the case of Haiti, and Japan earthquake. IBAD J Soc Sci, 12: 440-460. DOI: 10.21733/ibad.1039215.
11. İyigün C, Türkeş M, Batmaz İ, Yozgatlıgil C, Purutçuoğlu V, Kartal Koç E, Öztürk MZ. 2013. Clustering current climate regions of Turkey by using a multivariate statistical method. Theor Appl Climatol, 114: 95-106. DOI: 10.1007/s00704-012-0823-7.
12. Karahan H. 2011. Bölgesel yağış-şiddet-süre-frekans bağıntılarının diferansiyel gelişim algoritması kullanılarak elde edilmesi. TÜBİTAK (108Y299) Projesi Sonuç Raporu, Ankara, Türkiye.
13. Karahan H. 2019. Determination of Homogeneous Sub-Regions by Using intensity-duration-frequency relationships and cluster analysis: An application for the Aegean region. Pamukkale Univ Muh Bilim Derg, 25(8): 998-1013. DOI: 10.5505/pajes.2019.09365.
14. Kır G. 2021. Evaluation of the meteorological data of the Black Sea Region using clustering analysis methods. MSc Thesis, Ondokuz May University, Institute of Graduate Studies, Samsun, Türkiye, pp: 112.
15. Kite G. 1991. Looking for evidence of climatic change in hydrometeorological time series. Western Snow Conference, April 12-15, 1991, Juneau, Alaska, pp: 8-16.
16. Kulkarni A, Kripalani R. 1998. Rainfall patterns over India: Classification with fuzzy c-means method. Theor Appl Climatol, 59: 137-146. DOI: 10.1007/s007040050019.
17. Özkoca T. 2015. Trend analysis of hydrometeorological parameters at middle blacksea region coast band. MSc Thesis, Ondokuz May University, Graduate School of Natural and Applied Sciences, Samsun, Türkiye, pp: 89.
18. Öztürk MZ, Çetinkaya G, Aydın S. 2017. Köppen-Geiger iklim sınıflandırmasına göre Türkiye’nin iklim tipleri. Istanbul Univ J Geography, 35: 17-27. DOI: 10.26650/JGEOG295515.
19. Pal NR, Bezdek JC. 1995. On cluster validity for the fuzzy c-means model. IEEE Transact Fuzzy Syst, 3: 370-379. DOI: 10.1109/91.413225.
20. Rau P, Bourrel L, Labat D, Melo P, Dewitte B, Frappart F, Lavado W, Felipe O. 2017. Regionalization of rainfall over the Peruvian Pacific slope and coast. Int J Climatol, 37(1): 143-158. DOI: 10.1002/joc.4693.
21. Rousseeuw PJ. 1987. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math, 20: 53-65. DOI: 10.1016/0377-0427(87)90125-7.
22. Şahin S, Cığızoğlu HK. 2012. The sub-climate regions and the sub-precipitation regime regions in Turkey. J Hydrol, 450-451: 180-189. DOI: 10.1016/j.jhydrol.2012.04.062.
23. Şahin S. 2009. Applying artificial neural networks on determining climate zones and comparison with the Ward?s method. PhD Thesis, Istanbul Technical, Graduate School of Natural and Applied Sciences, İstanbul, Türkiye, pp: 347.
24. Soltani S, Modarres R. 2006. Classification of spatio temporal pattern of rainfall in Iran using a hierarchical and divisive cluster analysis. J Spatial Hydrol, 6(2): 1-12.
25. Sönmez İ, Kömüşcü A. 2008. Redefinition rainfall regions using k-means clustering methodology and changes of sub period. İklim Değiş Çevre, 1: 38-49.
26. Türkeş M. 1996. Spatial and temporal analysis of annual rainfall variations in Turkey. Int J Climatol, 16(9): 1057-1076.
27. Türkeş M. 2010. Küresel iklim değişikliği: Başlıca Nedenleri, gözlenen ve öngörülen değişiklikler ve etkileri. Uluslararası Katılımlı 1. Meteoroloji Sempozyumu, May 10-12, 2010, Ankara, Türkiye, pp: 9-38.
28. Ünal Y, Kındap T, Karaca M. 2003. Redefining the climate zones of Turkey using cluster analysis. Int J Climatol, 23: 1045-1055. DOI: 10.1002/joc.910.
29. Usta G. 2023 Statistical analysis of disasters in the world (1900-2022). Gümüşhane Univ J Soc Sci Inst, 14(1): 172-186.
30. Vani HY, Anusuya MA, Chayadevi ML. 2019. Fuzzy clustering algorithms-comparative studies for noisy speech signals. Ictact J Soft Comput, 9(3): 1920-1926. DOI: 10.21917/ijsc.2019.0267.
31. Zeybekoğlu U, Ülke Keskin A. 2020. Defining rainfall intensity clusters in Turkey by using the fuzzy c-means algorithm. Geofizika, 37(2): 181-195. DOI: 10.15233/gfz.2020.37.8.
32. Zhang Y, Wang W, Zhang X, Li Y. 2008. A cluster validity index for fuzzy clustering. Info Sci, 178: 1205-1218. DOI: 10.1016/j.ins.2007.10.004.