Sentinel 2 Uydu Görüntülerinden Bitki Türlerinin Makine Öğrenmesi ile Belirlenmesi

Uydu görüntülerinden bitki türlerinin sınıflandırılması tarım alanlarının yönetimi, gıda güvenliğinin sağlanması ve tarımsal politikaların oluşturulması için oldukça önemli bilgiler sağlar. Bitki türleri genel olarak uydu görüntülerinden hesaplanan vejetasyon indekslerine dayalı olarak veya çeşitli görüntü sınıflandırma teknikleri ile tahmin edilmektedir. Fakat bu yaklaşımlarda farklı bitkilerin benzer fenelojik ve spektral özelliklere sahip olması nedeniyle başarı oranı düşüktür. Bu nedenle bitki türlerinin uydu görüntüleri ile sınıflandırılması işleminde yeni, hassas ve daha başarılı bir yaklaşıma ihtiyaç duyulmaktadır. Bu çalışmanın amacı Rassal Orman (RO), Destek Vektör Makinesi (DVM) ve K-En Yakın Komşu (K-NN) makine öğrenme algoritmaları kullanılarak uydu görüntülerinden bitki türlerinin sınıflandırılmasıdır. Çalışma kapsamında 2020 yılı Gökhöyük Tarım İşletmesi Müdürlüğü’ ne ait tarım alanlarında yetiştirilen bitkilerin sınıflandırılmasında zaman serisi biçiminde Sentinel 2 uydu görüntüleri kullanılmıştır. Çalışmadan elde edilen sonuçlara göre en başarılı sınıflandırma (%95.3) RO ile hesaplanırken en düşük başarı DVM ile elde edilmiştir (%75.9). K-NN ile yapılan sınıflandırma başarısı ise %91.8 olarak hesaplanmıştır.

Anahtar Kelimeler:

makine öğrenmesi, rassal orman, destek vektör makinesi, k-en yakın komşu, bitki türü sınıflandırması, sentinel 2

Variations in Erosion Risk in Western Anatolia (Turkey): Modified Fournier Approach

As a result of global warming, more intense rainfall events and hence higher flood and erosion risk are expected to occur more likely. As erosion has been an important environmental problem in Turkey, it would be beneficial to document how it changed during global warming era. The aim of this study is to investigate the temporal evoluation of erosion risk from 1950 to 2018 in western Anatolia (Turkey), by using Modified Fournier Index (MFI). Also, temporal patterns of annual average temperature and annual total rainfall were analysed. The results, firstly, showed that the study area has cooled slightly from 1950 to 1976 and strongly warmed afterwards, which is consistent with the temporal pattern of global average temperature. Neither annual total rainfall nor MFI showed statistically significant tendencies during both periods. Erosion risk during the rapid warming period was not different from that in the cooling period. It follows that, on the contrary to the expectation, erosion risk in the study area stayed unchaged while average temperature increased substantially after mid-1970s.

Keywords:

Climate change, Erosion, Flood, Temperature, Ekstrem precipitation,

PDF

___

Baker, C (1987). Changes in financial markets and their effects on agriculture. Federal Reserve Bank of St. Louis Review.
Chan J C, Paelinckx D (2008). Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment. 112(6): 2999-3011.
Doğan Z, Arslan S, Berkman A N (2015). Türkiye'de Tarım Sektörünün İktisadi Gelişimi ve Sorunları: Tarihsel bir Bakış. Academic Review of Economics & Administrative Sciences. 8(1): 1308-4208.
Homer C, Huang C, Yang L, Wylie B, Coan M (2004). Development of a 2001 national land-cover database for the United States. Photogrammetric Engineering. 70(7): 829.
Hooda R S, Yadav M, Kalubarme M H (2006). Wheat production estimation using remote sensing data: An Indian experience. Workshop Proceedings: Remote Sensing Support to Crop Yield Forecast and Area Estimates, Stresa, Italy. 30 Nov.–1 Dec. 2006.
Jay S, Lawrence R, Repasky K, Keith C. (2009). Invasive species mapping using low cost hyperspectral imagery. ASPRS 2009 Annual Conference Baltimore, Maryland.
Kumar P, Gupta D K, Mishra V N, Prasad R (2015). Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data. International Journal of Remote Sensing. 36(6): 1604-1617.
Li L, Zheng X, Zhao K, Li X, Meng Z, Su C (2020). Potential Evaluation of High Spatial Resolution Multi-Spectral Images Based on Unmanned Aerial Vehicle in Accurate Recognition of Crop Types. Journal of the Indian Society of Remote Sensing.
Maxwell A E, Warner T A, Fang F (2018). Implementation of machine-learning classification in remote sensing: An applied review. IJRS. 39(9): 2784-2817.
MGM (2020). Meteoroloji Genel Müdürlüğü, Mevbis Sistemi.
Mountrakis G, Im J, Ogole C (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing. 66(3): 247-259.
Ok A O, Akar Ö, Güngör O (2012). Evaluation of Random Forest Method for Agricultural Crop Classification. European Journal of Remote Sensing. 45(1): 421-432.
Pal M, Foody G M (2010). Feature Selection for Classification of Hyperspectral Data by SVM. IEEE Transactions on Geoscience and Remote Sensing. 48(5): 2297-2307.
Pal M, Foody G M (2012). Evaluation of SVM, RVM and SMLR for accurate image classification with limited ground data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 5(5): 1344-1355.
Pal M, Mather P M (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote sensing of environment. 86(4): 554-565.
Pal M, Mather P M (2015). Support vector machines for classification in remote sensing. International journal of remote sensing. 26(5): 1007-1011.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011). Scikit-learn: Machine learning in Python. Journal of machine Learning research. 12: 2825-2830.
Prasad A M, Iverson L R, Liaw A. (2006). Newer Classification and Regression Tree Techniques: Bagging and Random Forests For Ecological Prediction. Ecosystems, 9: 181-199.
Scikit-learn (2020). Scikit-learn: Machine Learning in Python. https://scikit-learn.org
Uzundumlu A S (2012). Tarım Sektörünün Ülke Ekonomisindeki Yeri ve Önemi. Alinteri Journal of Agriculture Sciences. 22(1).
Waske B, Braun M (2009). Classifier Ensembles for Land Cover Mapping Using Multiemporal SAR Imagery. ISPRS Journal of Photogrammetry and Remote Sensing 64: 450–457.
Yang C, Everitt J H, Murden D (2011). Evaluating high resolution SPOT 5 satellite imagery for crop identification. Computers and Electronics in Agriculture. 75 (2): 347.