A New Perspective on Türkiye's Sheep Population: Classification with Decision Trees

Öz

Decision trees are data mining algorithms that make interpreting the cause-effect relationship or classification between features with visual diagrams easy and do not require parametric assumptions. The aim of this study is to classify different sheep breeds raised in Turkey according to their origin and tail structure characteristics using a decision tree algorithm. It has been seen that the CART (Classification and Regression Trees) algorithm is sufficient for the classification of sheep breeds by obtaining low-risk values. According to the results of the study, it is seen that domestic sheep breeds are distributed to Eastern Anatolia, Mediterranean, Black Sea, and Central Anatolia Regions and imported breeds are distributed to all regions of Türkiye. The total population of these breeds was determined as 43.889.918 heads. As it can be understood, the Akkaraman breed ranks first with a rate of 40.88% of the total sheep stock. Next comes the Morkaraman breed with a rate of 11.68%. Thirdly, the most cultivated breed is Kıvırcık, whose rate is 8.82%. Merino sheep comes in fourth place with 8.43%. Awassi sheep are among the most common breeds in the fifth place. Hereby the distribution of sheep breeds in Türkiye has also been revealed and the distribution of breeds according to environmental conditions has been determined. The decision tree model generated using the CART algorithm for the distribution of sheep breeds in Turkey based on tail structures has been found to have a value (0.47). The proportion of sheep with a thin tail structure is 52.2%, while those with a semi-fatty tail structure are 17.5%, and those with a fatty tail structure are 30.2%. It has been determined that sheep breeds with thin tails are more commonly raised in Turkey. In the study, a decision tree model was also created using the CART algorithm to analyze the distribution of sheep populations in regions based on their origin, and it was found to have a value (0.26) with an accuracy rate of 74%. According to the research, 73.9% of sheep are domestic, while 26.1% are imported. When examining the distribution of origin by region, the region with the least number of imported sheep is Eastern Anatolia, while the highest proportions are found in the Mediterranean and Black Sea regions. The region with the lowest proportion of domestic sheep is the Mediterranean and Black Sea (70.4%), whereas the highest proportion is in the Eastern Anatolia region (82.6%).

Anahtar Kelimeler

• Sheep number
• Classification
• Decision tree
• Sheep breeds

Teşekkür

We would like to thank the Izmir Provincial Director and Staff of the T.C. Ministry of Agriculture and Forestry, who helped carry out the study and share the current figures.

Türkiye Koyun Varlığına Yeni Bir Bakış: Karar Ağacı ile Sınıflama

Öz

Karar ağaçları özellikler arasındaki neden-sonuç ilişkisini ya da sınıflandırmayı görsel diyagramlarla kolay yorumlanmasını sağlayan, parametrik varsayımlara gerek duymayan veri madenciliği algoritmalarıdır. Bu çalışmanın amacı, Türkiye'de yetiştirilen farklı koyun ırklarının orijin ve kuyruk yapısı özelliklerine göre karar ağacı algoritması kullanarak sınıflandırmaktır. Düşük risk değerleri elde edilerek, koyun ırklarının sınıflandırılmasında CART algoritmasının yeterli olduğu görülmüştür. Çalışma sonuçlarına göre, yerli koyun ırklarının Doğu Anadolu, Akdeniz, Karadeniz ve İç Anadolu Bölgelerine ve ithal ırkların ise Türkiye’nin tüm bölgelerine dağıldığı görülmektedir. Bu koyun ırkların toplam popülasyonu 43.889.918 baş olarak belirlenmiştir. Toplam koyun varlığı içerisinde Akkaraman ırkı %40,88 oranı ile ilk sırada yer almaktadır. Bunu %11.68 oranla Morkaraman ırkı takip etmektedir. Üçüncü sırada ise en çok yetiştirilen tür %8.82 ile Kıvırcık koyunudur. Merinos koyunu ise %8.43 ile dördüncü sırada yer almaktadır. İvesi koyunları ise en yaygın ırklar arasında beşinci sırada yer almaktadır. Böylelikle koyun ırklarının Türkiye’deki dağılımı da ortaya konmuştur ve çevresel şartlara göre ırkların dağılımı belirlenmiştir. Türkiye'deki koyun ırklarının kuyruk yapılarına göre dağılımına ilişkin CART algoritması ile oluşturulan karar ağacı modelinin risk değeri düşük (0.47) bulunmuştur. İnce kuyruk yapısına sahip koyunların oranı %52.2 iken, yarı yağlı kuyruk yapısına sahip koyunların oranı %17,5, yağlı kuyruk yapısına sahip koyunların oranı ise %30.2'dir. Türkiye’ de ince kuyruklu koyun ırkları daha yaygın olarak yetiştirildiği belirlenmiştir. Çalışmada koyun varlığının kökenine göre göre bölgelere dağılımına yönelik CART algoritması ile oluşturulan karar ağacı modelinin risk değeri düşük bulunmuştur (0.26) ve doğru sınıflandırma oranı %74’ dir. Araştırmada koyunların yüzde 73.9'u yerli, yüzde 26.1'i ise ithal koyunlardan olduğu tespit edilmiştir. Bölgelere göre köken dağılımı incelendiğinde ithal koyun sayısının en az olduğu bölge Doğu Anadolu'da, en yüksek oranda ise Akdeniz ve Karadeniz bölgeleridir. Yerli koyun oranının en düşük olduğu bölge Akdeniz ve Karadeniz (%70.4) olurken, en yüksek oranın ise %82.6 ile Doğu Anadolu bölgesi olduğu belirlenmiştir.

Anahtar Kelimeler

• Koyun sayısı
• Sınıflandırma
• Karar ağacı
• Koyun ırkları

Kaynakça

1. Abu-Hanna, A. and De Keizer, N. (2003). Integrating classification trees with local logistic regression in Intensive Care prognosis. Artificial Intelligence in Medicine, 29(1-2): 5-23.
2. Acıbuca, V. and Bostan Budak, D. (2018). Place and Importance of Medicinal and Aromatic Plants in the World and Türkiye. Çukurova Tarım ve Gıda Bilimleri Dergisi. 33(1): 37- 44 (In Turkish).
3. Akşahan, R. and Keskin, İ. (2015). Determination of the somebody measurements effecting fattening final live weight of cattle by the regression tree analysis. Selçuk Tarım Bilimleri Dergisi, 2(1): 53-59.
4. Alev Çetin, F. and Mikail N. (2016). Data Mining Aplications in Livestock. Turkish Journal of Agricultural Research, 3(1): 79-88 (In Turkish).
5. Alpar, R. (2013). Applied Multivariate Statistical Methods. (4th Edition) Detay Publising, Ankara (In Turkish). Anonymous (2020). Meat and Milk Institution 2019 Sector Evaluation Report. https://www.esk.gov.tr/upload/Node/10255/files/2019_Yili_Sektor_Degerlendirme_Raporu.pdf (Accessed Date: 18.06.2020)
6. Anonymous (2021a). T.C Ministry of Agriculture and Forestry Animal Information System, (https://haybis.tarimorman.gov.tr/IsletmeGiris.aspx (Accessed Date: 02.01.2021)
7. Anonymous, (2021b). Türkiye Pet Genetic Resources Promotional Catalog. T.C. Ministry of Agriculture and Forestry https://www.tarimorman.gov.tr/TAGEM/Belgeler/yayin/Katalog%20T%C3%BCrk%C3%A7e.pdf (Accessed Date: 02.03.2021)
8. Balta, B. and Topal, M. (2018). Regression tree approach for assessing the effects of non-genetic factors on birth weight of Hemşin lamb. Alinteri Journal of Agriculture Science, 33(1): 65–7.

9. Breiman, L., Friedman, J. H., Olshen, R. A. and Stone, C. J. (1984). Classification and Regression Trees. Wadsworth International Group.
10. Cedden, F., Cemal, İ., Daşkıran, İ., Esenbuğa, N., Gül, S., Kandemi,r Ç., Karaca, O., Keskin, M., Koluman, N., Koyuncu, M., Savaş, T., Taşkın, T., Tölü, C., Ulutaş, Z., Yılmaz, O. and Yurtman, İ.Y. (2020). Current Situation and Future in Türkiye's Sheep Breeding. Turkish Agricultural Engineering IX. Technical Congress, 13-17 Ocak 2020, Ankara, s. 133-152 (In Turkish).
11. Cengiz F., Karaca S., Kor A., Ertuğrul M., Arık İ.Z. and Gökdal Ö. (2015). Changes and New Quests in Small Livestock Breeding. Turkish Agricultural Engineering VIII. Technical Congress, 12-16 Ocak 2015, TMMOB Chamber of Agricultural Engineering, C:2, 809-837, Ankara, 2015 (In Turkish).
12. Çaçan, E. and Yüksel, A. (2016). Influence of Meadows and Pastures on Regional Development. UNIDAP International Regional Development Conference, Muş, Türkiye. (In Turkish).
13. Çiçek, A., Ayyıldız, M., Erdal, G. and Erdal, H. (2022). Importance and economic analysis of sheep breeding in Türkiye. MAS Journal of Applied Sciences (Special İssue): 1303–1322 (In Turkish).
14. Demir, E. and Aygün, T. (2021). Characteristics of reproduction, milk and fleece yield of Hırik (Hamdani x Akkaraman crossbred) sheep raised in rural conditions. Journal of Animal Production, 62 (1), 35-44 (In Turkish).
15. Domingos, P. (1997). Why Does Bagging Work? A Bayesian Account and Its Implications. Proceedings of The Second International Conference On Knowledge Discovery and Data Mining, 155-165.
16. Eyduran, E., Karakus, K., Keskin, S. and Cengiz, F. (2008). Determination of factors influencing birth weight using regression tree method, Journal of Applied Animal Research 34: 109-112.
17. Eyduran, E., Zaborski, D., Waheed, A., Celik, S., Karadas, K., Grzesiak, W. (2017). Comparison of the predictive capabilities of several data mining algorithms and multiple linear regression in the prediction of body weight by means of body measurements in the indigenous Beetal goat of Pakistan. Pakistan Journal of. Zoology 49: 257-265.
18. Genuer, R., Poggi, J. M. and Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern recognition letters, 31(14): 2225-2236.
19. Güler, D. and Saner, G. (2021). The measurement of efficiency of dairy farms: The cases of Izmir and Manisa. Yuzuncu Yıl University Journal of Agricultural Sciences, 30(2): 386-397. (In Turkish).
20. Hanoğlu, Oral.H., Kuz, H.İ., Dayanıklı, C., Önaldı, A.T., Alarslan, E. and Duman, E. (2021). Structural characteristics of extensive small ruminant farms and transition opportunities to organic animal husbandry: The Case of Balıkesir province, Türkiye. Turkish Journal of Agricultural Research, 8(3): 320-330. (In Turkish).
21. Hastie, T., Tibshirani, R. and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Science & Business Media.
22. İzmir Commodity Exchange. (2019). Future of Sheep Farming in Türkiye and Sustainable Production Project. Workshop Final Report, 31 January 2019, İzmir (In Turkish).
23. Kahraman, M. and Yüceer Özkul. B. (2020). Investigation of milk fatty acid profiles in some domestic and hybrid sheep genotypes. Harran University Journal of the Faculty of Veterinary Medicine, 9(2): 126-132. (In Turkish).
24. Kalaycı, Ş. (2006). SPSS Applied Multivariate Statistics Techniques. (2th Edition), Asil Publishing Distribution, Ankara. (In Turkish).
25. Kandemir, Ç., Alkan, İ., Yılmaz, H.İ., Ünal, H.B., Taşkın, T., Koşum, N. and Alçiçek, A. (2015). General situation and development opportunities to the geographical locations of small ruminant farms in İzmir Region. Journal of Animal Production, 56(1):1-17 (In Turkish).
26. Kandemir, Ç., Adanacıoğlu, H., Taşkın, T. and Koşum, N. (2019). Sheep and sheep meat prices of comparison analysis of scaling. Journal of Tekirdag Agricultural Faculty, 16(3), 315-327 (In Turkish).
27. Kandemir, Ç. and Taşkın, T. (2022a). Current situation of sheep breeds raised in the Eastern Anatolia Region Journal of Animal Production, 63 (1): 57-65 (In Turkish).
28. Kandemir, Ç. and Taşkın, T. (2022b). Current situation and future of sheep breeds: Mediterranean Region. Turkish Journal of Agricultural Research 9(1): 97-106 (In Turkish).
29. Kandemir, Ç. and Taşkın, T. (2022c). Current state and future of sheep breeds in Türkiye: Blacksea Region. Van Yuzuncu Yil University Institute of Natural and Applied Sciences. 27(1):101-112 (In Turkish).
30. Kandemir, Ç. and Taşkın, T. (2022d). Status of sheep breeds by regions in Türkiye: Central Anatolia Region. International Journal of Anatolia Agricultural Engineering Sciences, 4(4): 97-105 (In Turkish).
31. Kandemir, Ç. and Taşkın, T. (2022e). Current situation of native and cultured sheep breeds in the Marmara Region. Voice of Nature, 5(9): 17-33 (In Turkish).
32. Karakoç, T. and Aygün, T. (2019). The live weight after shearing and the greasy wool yield of Zom ewes at different raising conditions in Türkiye. Journal of Advanced Agricultural Technologies, 6(4): 267-271.
33. Karaman, S. (2018). Comparative analysis of turkey's crop and livestock productıon values at regional level using a panel data index. Yuzuncu Yıl University Journal of Agricultural Sciences. 28(2):168-174 (In Turkish).
34. Kaymakçı, M. and Taşkın, T. (2008). Sheep crossbreeding studies in Türkiye. Journal of Animal Production, 49 (2), 43-51 (In Turkish).
35. Kayri, M. and Boysan M. (2008). Assesment of relation between cognitive vulnerability and depression’s level by using classification and regression tree analysis Harran University Journal of Education, 34: 168-177 (In Turkish).
36. Keskinkılıç, K. (2019). Sustainability of Sheep Farming Activity. Izmir Commodity Exchange Publications No:99, İzmir. p:195 (In Turkish).
37. Kırbaş, M., Bülbül, B. and Kal, Y. (2022). Some reproductive traits in Central Anatolian Merino sheep under breeder conditions. Journal of Advances in Veterinary Bio Science and Techniques, 7(1), 14-18 (In Turkish).
38. Kononenko, I. and Kukar, M. (2007). Machine Learning and Data Mining: Introduction to Principles and Algorithms. Horwood Publishing.
39. Kuşvuran, A., Nazlı, R.İ. and Tansı, V. (2011). Current situation of meadow-rangelands, animal existence and cultivation for forage crops in Türkiye and East Black Sea Region. Journal of Agricultural Faculty of Gaziosmanpaşa University, 28(2), 21-32 (In Turkish).
40. Mendeş, M and Akkartal E. (2009). Regression tree analysis for predicting slaughter weight in broilers. Italian Journal of Animal Science, 8(4):615-624.
41. MFAL. (2023). Minestery of Food and Agricultutal and Livestock. (Accessed Date:02.03.2021)
42. Oğul, B. (2022). The relationship of agricultural subsidies and agricultural production: empirical findings on the Turkish economy. The Journal of Agricultural Economics Researches, 8(1): 44-56 (In Turkish).
43. Olfaz, M., Tırınk, C. and Önder, H. (2019). Use of CART and CHAID algorithms in Karayaka sheep breeding. Kafkas Universitesi Veteriner Fakültesi Dergisi, 25(1): 105–110.
44. Oruçoğlu, O. (2011). Determination of environmental factors affecting 305-day milk yield of Holstein cows by regression tree method. (MSc Thesis) Süleyman Demirel University, Institute of Science and Technology, Isparta, Türkiye. (In Turkish)
45. Özsayın, D. and Everest, B. (2019). Socio-economic structure of farmers that make sheep breeding and practices related to their sheep breeding activities. Journal of Agriculture and Nature, 22 (Supplementary Issue 2): 440-448. (In Turkish)
46. Quinlan, J. R. (1985). Decision Trees and Multi-Valued Attributes. In J. E. Hayes and D. Michie (Eds.), Machine intelligence 11. Oxford University Press.
47. Semerci, A. and Çelik, A.D. (2016). General overview of ovine breeding in Türkiye. Journal of Agricultural Faculty of Mustafa Kemal University, 21(2): 182-196. (In Turkish)
48. Sevgenler H. (2019). Comparison of data mining algorithms (Cart, Chaid and Mars) used to determine the effects of some characteristics of goats on live weight. (MSc Thesis) Iğdır University, Institute of Science, Department of Animal Science, Iğdır, Türkiye. (In Turkish).
49. Sevinç G., Şahin Z. and Aydoğdu M.H. (2022). The trend analysis of the developments of ovine presence and its milk production in Türkiye. Journal of Academic Social Resources, 7(35): 377-38. (In Turkish)
50. Sezenler T., Soysal, D., Yildirir, M., Yüksel, M. A., Ceyhan, A., Yaman Y., Erdoğan İ. and Karadağ O. (2013). Influence of some environmental factors on litter size and lamb growth performance in Karacabey Merino sheep. Journal of Tekirdağ Agricultural Faculty,10(1): 40-47. (In Turkish)
51. Sönmez, R., Kaymakçı, M., Eliçin, A., Tuncel, E., Wassmuth, R. and Taşkın, T. (2009). Improvement Studies in Türkiye Sheep Husbandry. Türkiye Sheep Breeding Congress, 12-13 Şubat 2009, İzmir, Türkiye. (In Turkish).
52. Tamer, B. and Sarıözkan, S. (2017). Socio-economic structure and production costs of sheep farms in central district of Yozgat province. Journal of The Faculty of Veterinary Medicine Erciyes University, 14(1): 39-47. (In Turkish).
53. Taşkın, T. and Kandemir, Ç. (2022a). Current situation and future of sheep breeds: Aegean Region. Journal of Agriculture Faculty of Ege University, 59 (3):485-498. (In Turkish).
54. Taşkın, T. and Kandemir, Ç. (2022b). Current state and future of sheep breeds in Türkiye: Southeast Anatolia Region. Journal of Kadirli Faculty of Applied Sciences, 2(1): 93-105. (In Turkish).
55. Taşkın, T., Ünal, H. B. and Canbolat, Ö. (2015). Basic Principles of Sheep Breeding. Hasad Publishing. Ltd. Şti, Ümraniye-İstanbul (In Turkish).
56. Temel, Ö. G. (2004). Classification and regression trees. (MSc Thesis) Mersin University, Health Information Institute, Department of Biostatistics, Mersin, Türkiye. (In Turkish).
57. Türkiye İstatistik Kurumu (2023). Livestock data, https://biruni.tuik.gov.tr/medas/?kn=101&locale=tr (Accessed Date: 09.10.2023)
58. Yakar, M. and Özgür, E. M. (2022). The aging population in Türkiye is ringing alarm bells at the local level. Journal of Geography, (44): 231-250 (In Turkish).
59. Yılmaz, Ş. G. (2019). Socio-economic analysis and efficiency of small livestock enterprises: the example of the Western Mediterranean Region. (PhD Thesis) Isparta University of Applied Sciences Institute of Science, Isparta, Türkiye. (In Turkish).