Nesne tabanlı Sınıflandırma ve Regresyon Ağacı kullanılarak Ağyatan sulak alanının mevsimsel kıyı dinamiklerinin izlenmesi

Year 2025, Volume: 14 Issue: 1, 308 - 317, 15.01.2025

Mustafa Hayri Kesikoğlu , Tolga Kaynak

https://doi.org/10.28948/ngumuh.1559034

Abstract

Son yıllarda su ve sulak alanların yönetimi giderek önem kazanmıştır. Ağyatan Sulak Alanı, Ceyhan Nehri'nin batısında yer alan doğal bir göldür. Sulak alan çevresi çeşitli deniz ve kara canlılarına, endemik bitkilere ve nesli tükenmekte olan kuşlara ev sahipliği yapmaktadır. Bu çalışmada, 2016 yılında Ağyatan Sulak Alanı'nda meydana gelen mevsimsel değişimlerin analizi amaçlanmıştır. Bu değişimlerin belirlenmesi için 2016 yılının dört farklı mevsimine ait Landsat 8 görüntüleri kullanılmıştır. Çalışma alanları göl, deniz, ekili tarım arazisi, çıplak alan, yapı alanı ve su kanalı olmak üzere altı kategoriye ayrılmıştır. Dört mevsime ait tematik haritalar, nesne tabanlı Sınıflandırma ve Regresyon Ağacı (CART) yöntemi kullanılarak üretilmiştir. Ayrıca, sınıflandırma sonrası karşılaştırma yöntemi kullanılarak değişim tespiti analizleri yapılmıştır. Çalışmada, 2016 yılında göl alanında kıştan ilkbahara doğru (0.8919%) bir azalma, ardından ilkbahardan yaza (0.3627%) ve yazdan sonbahara (0.1953%) doğru bir artış olduğu ortaya konulmuştur. Bu dalgalanmanın yeraltı suyuna, nehir suyuna ve eriyen karlara bağlandığı belirtilmiştir.

Keywords

Değişim belirleme, nesne tabanlı sınıflandırma, CART, sulak alan, Landsat 8, uydu görüntüsü

Tracking seasonal coastal dynamics of Ağyatan wetland using object-based Classification and Regression Tree

Abstract

In recent years, the management of water and wetlands has become increasingly important. Ağyatan Wetland is a natural lake formed by the Ceyhan River, located west of the river. The area around the wetland is home to various sea and land creatures, as well as endemic plants and endangered birds. This study aimed to analyze the seasonal changes occurring in the Ağyatan wetland in 2016. Landsat 8 images from four seasons of 2016 were utilized to identify these changes. The study areas were classified into six categories: lake, sea, cultivated agricultural land, barren land, building area, and water channel. Thematic maps for the four seasons were generated using the object-based Classification and Regression Tree (CART) method. Additionally, change detection analyses were conducted using the post-classification comparison method. The study revealed a decrease in the lake area from winter to spring (0.8919%), followed by an increase from spring to summer (0.3627%) and summer to autumn (0.1953%) in 2016. This fluctuation was attributed to groundwater, river water, and melting snow.

Keywords

Change detection, object-based classification, CART, wetland, Landsat 8, satellite image

References

• A. Delen ve F. Balık Şanlı, Nesne tabanlı sınıflandırma yöntemi ile tarımsal ürün deseninin belirlenmesi. TUFUAB IX. Teknik Sempozyumu, Afyonkarahisar, 2017.
•     M. Gholoobi, A. Tayyebi , M. Taleyi and A. H. Tayyebi, Comparing pixel based and object based approaches ın land use classification ın mountainous areas. International Archives of the Photogrammetry. Remote Sensing and Spatial Information Science.Volume XXXVIII. Part 8. Kyoto. Japan, 2010.
•     K. Kalkan ve D. Maktav, Nesne tabanlı ve piksel tabanlı sınıflandırma yöntemlerinin karşılaştırılması (IKONOS Örneği). III. Uzaktan Algılama ve Coğrafi Bilgi Sistemleri Sempozyumu, Gebze, 2010.
•     S. Wang, S. He, J. Wang, J. Li, X. Zhong, J. Cole, E. Kurbanov, and J. Sha, Analysis of Land Use/Cover changes and driving forces in a typical subtropical region of South Africa. Remote Sensing, 15(19), 4823, 2023. https://doi.org/10.3390/rs15194823.
•     M. Aghababaei, A. Ebrahimi, A. A. Naghipour, E. Asadi, and J. Verrelst, Classification of plant ecological units in heterogeneous semi-steppe rangelands: performance assessment of four classification algorithms. Remote Sensing, 13(17), 3433, 2021. https://doi.org/10.3390/rs13173433.
•     P. Turissa, N. Bisman, S. Vincentius, K. Dony and M. Hawis, Evaluation methods of change detection of seagrass beds in the waters of Pajenekang and Gusung Selayar. Trends in Sciences, 18(23), 677, 2021. https://doi.org/10.48048/tis.2021.677.
•     E. E. Tonyaloğlu, N. Erdogan, B. Çavdar, K. Kurtşan, and E. Nurlu, Comparison of pixel and object based classification methods on rapideye satellite image. Turkish Journal of Forest Science, 5(1), 1-11, 2021. https://doi.org/10.32328/turkjforsci.741030.
•     L. A. Qu, Z. Chen, M. Li, J. Zhi, and H. Wang, Accuracy Accuracy improvements to pixel-based and object-based lulc classification with auxiliary datasets from Google Earth engine. Remote Sensing, 13(3), 453, 2021. https://doi.org/10.3390/rs13030453.
•     T. Tochamnanvita and W. Muttitanon, Investigation of coastline changes in three provinces of Thailand using remote sensing. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(8), 1079, 2014. https://doi.org/10.5194/isprsarchives-XL-8-1079-2014.
•   M. Modi, R. Kumar, G. R. Shankar and T. R. Martha, Land cover change detection using object-based classification technique: a case study along The Kosi River, Bihar. The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences, Volume XL-8, ISPRS Technical Commission VIII Symposium, Hyderabad, India, 2014.
•   H. M. Badjana, J. Helmschrot, P. Selsam, K. Wala, W. A. Flügel, A. Afouda, and K. Akpagana, Land cover changes assessment using object-based image analysis in the Binah River watershed (Togo and Benin). Earth and Space Science, 2(10), 403-416, 2015. https://doi.org/10.1002/2014EA000083.
•   E. Sánchez-García, J. E.Pardo-Pascual, A. Balaguer-Beser, and J. Almonacid-Caballer, Analysis of the shoreline Position Extracted from Landsat TM and ETM+ Imagery. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(7), 991, 2015. https://doi.org/10.5194/isprsarchives-XL-7-W3-991-2015.
•   X. Lin, Y. Cheng, G. Chen, W. Chen, R. Chen, D. Gao D, Y. Zhang, and Y. Wu, Semantic segmentation of China’s coastal wetlands based on Sentinel-2 and Segformer. Remote Sensing, 15(15), 3714, 2023. https://doi.org/10.3390/rs15153714.
•   A. Gonzalez-Perez, A. Abd-Elrahman, B. Wilkinson, D. J. Johnson, and R. R. Carthy, Deep and machine learning image classification of coastal wetlands using unpiloted aircraft system multispectral images and lidar datasets. Remote Sensing, 14(16), 3937, 2022. https://doi.org/10.3390/rs14163937.
•   R. Zhou, C. Yang, E. Li, X. Cai, J. Yang, and Y. Xia, Object-based wetland vegetation classification using multi-feature selection of unoccupied aerial vehicle RGB imagery. Remote Sensing, 13(23), 4910, 2021. https://doi.org/10.3390/rs13234910.
•   S. Adeli, B. Salehi, M. Mahidanpari, and L. J. Quackenbush, Toward a multi-source remote sensing wetland inventory of the USA: preliminary results on wetland inventory of Minnesota. ISPRS annals of the photogrammetry remote sensing and spatial information sciences, 3, 97-100, 2021. https://doi.org/10.5194/isprs-annals-V-3-2021-97-2021.
•   M. H. Kesikoglu, U. H. Atasever, F. Dadaser-Celik, and C. Ozkan, Performance of ANN, SVM and MLH techniques for land use/cover change detection at Sultan Marshes wetland, Turkey. Water Science and Technology, 80(3), 466-77, 2019. https://doi.org/10.2166/wst.2019.290.
•   O. O. Festus, W. Ji, and O. A. Zubair, Characterizing the landscape structure of urban wetlands using terrain and landscape indices. Land, 9(1), 29, 2020. https://doi.org/10.3390/land9010029.
•   H. Ç. Çiftçi, K. Gümüş, and M. G. Gümüş, Analyzing land use and climate change impacts of Suğla water storage in Turkey. Theoretical and Applied Climatology, 155(7), 6797-6814, 2024. https://doi.org/10.1007/s00704-024-05043-0.
•   T. Feng, H. Ma, and X. Cheng, Land-cover classification of high-resolution remote sensing image based on multi-classifier fusion and the improved Dempster–Shafer evidence theory. Journal of Applied Remote Sensing, 15(1), 014506-014506, 2021. https://doi.org/10.1117/1.JRS.15.014506.
•   J. P. Simioni, L. A. Guasselli, G. G. De Oliveira, L. F. Ruiz, and G. De Oliveira,  A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation. Wetlands Ecology and Management, 28(4), 577-594, 2020. https://doi.org/10.1007/s11273-020-09731-2.
•   M. Mahdianpari, B. Brisco, J. E. Granger, F. Mohammadimanesh, B. Salehi, S. Banks, S. Homayouni, L. Bourgeau-Chavez, and Q. Weng, The second generation Canadian wetland inventory map at 10 meters resolution using Google Earth Engine. Canadian Journal of Remote Sensing, 46(3), 360-375, 2020. https://doi.org/10.1080/07038992.2020.1802584.
•   S. Gxokwe, T. Dube, and D. Mazvimavi, Leveraging Google Earth Engine platform to characterize and map small seasonal wetlands in the semi-arid environments of South Africa. The Science of the Total Environment, 803, 150139, 2022. https://doi.org/10.1016/j.scitotenv. 2021.150139.
•   F. Büyükdeveci, Türkiye’nin Doğu Akdeniz kıyısında bulunan Ağyatan (Hurma Boğazı) lagününde yakalanan türlerin av kompozisyonu ve av verimi. Journal of Anatolian Environmental and Animal Sciences, 8(3), 559-567, 2023. https://doi.org/ 10.35229/jaes.1350126.
•   M. A. Çelik, Y. Kızılelma, A. E. Gülersoy, ve M. Denizdurduran, Farklı uzaktan algılama teknikleri kullanılarak aşağı Seyhan ovası güneyindeki sulak alanlarda meydana gelen değişimin incelenmesi (1990-2010). Electronic Turkish Studies, 8(12), 263-284, 2013.
•   United States Geological Survey (USGS), EarthExplorer. https://earthexplorer.usgs.gov/, Accessed 13 March 2017.
•   United States Geological Survey (USGS), What are the band designations for the Landsat satellites? http://landsat.usgs.gov/band_designations_landsat_satellites.php, Accessed 13 March 2017.
•   Ç. Göksel, R. M. David, and A. O. Dogru, Environmental monitoring of spatio-temporal changes in northern Istanbul using remote sensing and GIS. International Journal of Environment and Geoinformatics, 5(1), 94-103, 2018. https://doi.org/10.30897/ijegeo.410943.
•   C. Witharana, and D. L. Civco, Optimizing multi-resolution segmentation scale using empirical methods: Exploring the sensitivity of the supervised discrepancy measure Euclidean distance 2 (ED2). ISPRS Journal of Photogrammetry and Remote Sensing, 87, 108-121, 2014. https://doi.org/10.1016/j.isprsjprs.2013.11.006.
•   M. H. Kesikoglu, U. H. Atasever, C. Ozkan, and E. Besdok, The usage of rusboost boosting method for classification of impervious surfaces. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 41, 981-985, 2016. https://doi.org/10.5194/isprs-archives-XLI-B7-981-2016.
•   P. Z. Firouzabadi and E. Ghanavati, Digital approaches for change detection in urban environment, Geographical Research, 22(1), 84, 133-146, 2007.
•   M. H. Kesikoğlu, Ü. H. Atasever, and C. Özkan, Unsupervised change detection in satellite images using fuzzy c-means clustering and principal component analysis. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40, 129-132, 2013. https://doi.org/10.5194/isprsarchives-XL-7-W2-129-2013.
•   L. Bruzzone, and D.Prieto, Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote sensing, 38(3), 1771-1182, 2000.
•   F. Pacifici, F. D. Frate, C. Solimini, and W. Emery, An innovative neural-net method to detect temporal changes in high-resolution optical satellite imagery. IEEE Transactions on Geoscience and Remote Sensing, 45(9), 2940–2952, 2007. https://doi.org/ 10.1109/TGRS.2007.902824.
•   Climate Data, İklim Karataş (Türkiye). https://tr.climate-data.org/location/26497/, Accessed 20 May 2017.
•   F. Mohseni, M. Amani, P. Mohammadpour, M. Kakooei, S. Jin, and A. Moghimi, Wetland mapping in great lakes using Sentinel-1/2 time-series imagery and DEM data in Google Earth Engine. Remote Sensing, 15(14), 3495, 2023. https://doi.org/10.3390/ rs15143495.
•   X. B. Tran, V. Vambol, and T. D. Luu, Assessing forest cover changes in Dak Lak province (Central Highlands of Vietnam) from multi-temporal Landsat data and machine learning techniques. Ecological Questions, 35(3), 1-18.  https://doi.org/10.12775/EQ.2024.035.
•   T. K. Oo, N. Arunrat, S. Sereenonchai, A. Ussawarujikulchai, U. Chareonwong, and W. Nutmagul, Comparing four machine learning algorithms for land cover classification in gold mining: A case study of Kyaukpahto Gold Mine, Northern Myanmar, Sustainability, 14(17), 10754, 2022. https://doi.org/10.3390/su141710754.
•   S. Aldiansyah, and R. A. Saputra, Comparison of machine learning algorithms for land use and land cover analysis using Google Earth engine (Case study: Wanggu watershed). International Journal of Remote Sensing and Earth Sciences, 19(2), 197-210, 2023.
•   C. U. Rahayu, I. Indarto, and B. E. Cahyono, Using sentinel and comparing two classification algorithms for land cover mapping in the area dominated by small scale heterogeneous agricultural land. IOP Conference Series: Earth and Environmental Science, Bristol, UK, 2022.