Research Article
BibTex RIS Cite

Türkiye İçin Küresel Arazi Kullanımı/Örtüsü Haritalarının Doğruluğunun Değerlendirilmesi: ESA World Cover ve ESRI Land Cover Karşılaştırması

Year 2025, Volume: 27 Issue: 2, 223 - 238
https://doi.org/10.24011/barofd.1666812

Abstract

Arazi kullanımı ve arazi örtüsü (LULC) sınıflandırması, çevresel değişimlerin izlenmesi, ekosistem dinamiklerinin anlaşılması ve sürdürülebilir arazi yönetiminin desteklenmesi açısından kritik bir rol oynamaktadır. Uzaktan algılama teknolojilerindeki ilerlemelerle birlikte, küresel LULC veri setleri geniş ölçekli çevresel değerlendirmeler için temel bir araç haline gelmiştir. Bu çalışmada, 2021 yılı için ESA WorldCover ve ESRI Land Cover veri setlerinin Türkiye’de sekiz farklı coğrafi havzadaki örneklem alanlar üzerinde doğruluk değerlendirmesi gerçekleştirilmiştir. Çalışma kapsamında, Sentinel-1/2 verilerine dayalı olarak üretilen ESA WorldCover 2021 ve yalnızca Sentinel-2 optik verilerini kullanan ESRI Land Cover 2021 veri setleri karşılaştırılmıştır. Değerlendirme metrikleri olarak genel doğruluk (OA), Kappa katsayısı, üretici doğruluğu (ÜD) ve kullanıcı doğruluğu (KD) hesaplanmıştır. Sonuçlar, ESA WorldCover 2021’in tüm havzalarda ESRI Land Cover 2021’e kıyasla daha yüksek doğruluk sunduğunu ortaya koymuştur. En yüksek genel doğruluk ESA WorldCover için %93,00 ile Güney Doğu Anadolu bölgesinde yer alan H7 havzasında, ESRI Land Cover için ise %87,74 ile Doğu Anadolu bölgesinde yer alan H8 havzasında elde edilmiştir. ESA veri seti, radar ve optik verileri entegre etmesi sayesinde su yüzeyleri, ağaç örtüsü ve tarım alanlarının sınıflandırma başarısı daha yüksek hesaplanmıştır. Öte yandan, ESRI Land Cover’ın yalnızca optik verilere dayalı olması, bulut örtüsüne duyarlılığı artırmış ve özellikle heterojen arazi yapısına sahip bölgelerde hata oranlarını yükseltmiştir. Bu çalışma, küresel LULC veri setlerinin doğruluklarının bölgesel ölçekte karşılaştırılması açısından önemli bir katkı sunmaktadır. Elde edilen bulgular, karar vericilerin bu veri setlerini referans alarak arazi yönetimi, çevresel değişim izleme, doğal kaynakların korunması ve sürdürülebilir kalkınma politikalarının oluşturulması gibi süreçlerde daha bilinçli ve güvenilir kararlar almasına olanak sağlayacaktır.

Supporting Institution

TÜBİTAK

Thanks

Bu çalışmada TÜBİTAK–2209-A Üniversite Öğrencileri Araştırma Projeleri Desteği Programı tarafından desteklenen “Global 10 m Arazi Kullanımı Arazi Örtüsü Veri Setlerinin Doğruluk Değerlendirilmesi; ESA World Cover ve ESRI Land Cover” isimli proje kapsamındaki verilerden yararlanılmıştır. Ayrıca çalışmanın özeti TUFUAB XIII. Teknik Sempozyumu’na gönderilmiş ve sözlü bildiri olarak sunulmuştur.

References

  • Altürk, B. (2023). Accuracy assessment of different land use/land cover maps: A case study of TR21 Thrace region.
  • Bégué, A., Arvor, D., Bellon, B., Betbeder, J., De Abelleyra, D., Ferraz, R. P. D., Lebourgeois, V., Lelong, C., Simões, M., ve Verón, S. R. (2018). Remote sensing and cropping practices: A review. Remote Sensing, 10(1), 99. https://doi.org/10.3390/rs10010099.
  • Bie, Q., Luo, J., ve Lu, G. (2023). Accuracy performance of three 10-m global land cover products around 2020 in an arid region of northwestern China. IEEE Access, 11, 133215-133228.
  • Chaaban, F., El Khattabi, J., ve Darwishe, H. (2022). Accuracy assessment of ESA WorldCover 2020 and ESRI 2020 land cover maps for a region in Syria. Journal of Geovisualization and Spatial Analysis, 6(2), 31.
  • Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37-46.
  • Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46. https://doi.org/10.1016/0034-4257(91)90048-B.
  • Efe, E., ve Algancı, U. (2023). Çok zamanlı Sentinel 2 uydu görüntüleri ve makine öğrenmesi tabanlı algoritmalar ile arazi örtüsü değişiminin belirlenmesi. Geomatik, 8(1), 27-34.
  • Fritz, S., ve See, L. (2005). Comparison of land cover maps using fuzzy agreement. International Journal of Geographical Information Science, 19(7), 787-807.
  • GEE. (2025). GEE ESRI 10m annual land cover (2017–2023). Erişim adresi: https://gee-community-catalog.org/projects/S2TSLULC/.
  • Van Genderen, J. L., ve Lock, B. F. (1977). Testing land-use map accuracy. Photogrammetric Engineering and Remote Sensing, 43(9), 1135-1137.
  • Van Genderen, J. L., Lock, B. F., ve Vass, P. A. (1978). Remote sensing: Statistical testing of thematic map accuracy. Remote Sensing of Environment, 7(1), 3-14.
  • Hadi, S. J., Shafri, H. Z. M., ve Mahir, M. D. (2014). Modelling LULC for the period 2010–2030 using GIS and remote sensing: A case study of Tikrit, Iraq. IOP Conference Series: Earth and Environmental Science, 20, 012053.
  • Hassan, M. M., ve Nazem, M. N. I. (2016). Examination of land use/land cover changes, urban growth dynamics, and environmental sustainability in Chittagong City, Bangladesh. Environment, Development and Sustainability, 18(3), 697-716.
  • Karra, K., Kontgis, C., Statman-Weil, Z., Mazzariello, J. C., Mathis, M., ve Brumby, S. P. (2021). Global land use/land cover with Sentinel 2 and deep learning. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (pp. 4704-4707). IEEE.
  • Liping, C., Yujun, S., ve Saeed, S. (2018). Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—A case study of a hilly area, Jiangle, China. PloS One, 13(7), e0200493.
  • Maingi, J. K., Kepner, S. E., & Edmonds, W. G. (2002). Accuracy Assessment of 1992 Landsat-MSS Derived Land Cover for the Upper San Pedro Watershed(US/Mexico). Sponsored by Environmental Protection Agency, Las Vegas, NV. National Exposure Research Lab, 2002.
  • Olofsson, P., Foody, G. M., Stehman, S. V., & Woodcock, C. E. (2013). Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sensing of Environment, 129, 122-131.
  • Rwanga, S. S., ve Ndambuki, J. M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences, 8(4), 611-622.
  • San Miguel-Ayanz, J., & Biging, G. S. (1997). Comparison of single-stage and multi-stage classification approaches for cover type mapping with TM and SPOT data. Remote Sensing of Environment, 59(1), 92-104. Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 62(1), 77-89.
  • Venter, Z. S., Barton, D. N., Chakraborty, T., Simensen, T., ve Singh, G. (2022). Global 10 m land use land cover datasets: A comparison of Dynamic World, WorldCover and Esri land cover. Remote Sensing, 14(16), 4101.
  • Zanaga, D., Van De Kerchove, R., Daems, D., De Keersmaecker, W., Brockmann, C., Kirches, G., Wevers, J., Cartus, O., Santoro, M., ve Fritz, S. (2022). ESA WorldCover 10 m 2021 V200.

Evaluating the Accuracy of Global Land Cover Maps for Türkiye: A Comparison of ESA World Cover and ESRI Land Cover

Year 2025, Volume: 27 Issue: 2, 223 - 238
https://doi.org/10.24011/barofd.1666812

Abstract

Land use and land cover (LULC) classification play a crucial role in monitoring environmental changes, understanding ecosystem dynamics, and supporting sustainable land management. With advancements in remote sensing technologies, global LULC datasets have become essential tools for large-scale environmental assessments. This study evaluates the accuracy of the ESA WorldCover 2021 and ESRI Land Cover 2021 datasets across eight distinct geographical watersheds in Türkiye. The study compares ESA WorldCover 2021, which integrates Sentinel-1 and Sentinel-2 data, with ESRI Land Cover 2021, which relies solely on Sentinel-2 optical data. Accuracy assessment was conducted using stratified random sampling and visual interpretation with high-resolution Google Earth imagery. Evaluation metrics included overall accuracy (OA), Kappa coefficient, producer accuracy (PA), and user accuracy (UA). The findings indicate that ESA WorldCover 2021 outperformed ESRI Land Cover 2021 in all watersheds. The highest OA for ESA WorldCover was 93.00% in watershed H7 (Southeastern Anatolia), while ESRI Land Cover achieved 87.74% in watershed H8 (Eastern Anatolia). The integration of radar and optical data in ESA WorldCover enhanced classification accuracy for water bodies, tree cover, and croplands. Conversely, the reliance of ESRI Land Cover on optical data alone increased susceptibility to cloud cover, leading to higher misclassification rates, particularly in heterogeneous landscapes. This study provides valuable insights into the regional accuracy of global LULC datasets. The findings will assist decision-makers in selecting the most reliable dataset for applications in land management, environmental monitoring, natural resource conservation, and sustainable development planning.

Supporting Institution

TUBITAK

Thanks

This study utilized data from the "Accuracy Assessment of Global 10 m Land Use and Land Cover Datasets; ESA World Cover and ESRI Land Cover" project, supported by the TÜBİTAK-2209-A University Student Research Projects Support Program. A summary of the study was also submitted to the TUFUAB XIIIth Technical Symposium and presented as an oral presentation.

References

  • Altürk, B. (2023). Accuracy assessment of different land use/land cover maps: A case study of TR21 Thrace region.
  • Bégué, A., Arvor, D., Bellon, B., Betbeder, J., De Abelleyra, D., Ferraz, R. P. D., Lebourgeois, V., Lelong, C., Simões, M., ve Verón, S. R. (2018). Remote sensing and cropping practices: A review. Remote Sensing, 10(1), 99. https://doi.org/10.3390/rs10010099.
  • Bie, Q., Luo, J., ve Lu, G. (2023). Accuracy performance of three 10-m global land cover products around 2020 in an arid region of northwestern China. IEEE Access, 11, 133215-133228.
  • Chaaban, F., El Khattabi, J., ve Darwishe, H. (2022). Accuracy assessment of ESA WorldCover 2020 and ESRI 2020 land cover maps for a region in Syria. Journal of Geovisualization and Spatial Analysis, 6(2), 31.
  • Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37-46.
  • Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46. https://doi.org/10.1016/0034-4257(91)90048-B.
  • Efe, E., ve Algancı, U. (2023). Çok zamanlı Sentinel 2 uydu görüntüleri ve makine öğrenmesi tabanlı algoritmalar ile arazi örtüsü değişiminin belirlenmesi. Geomatik, 8(1), 27-34.
  • Fritz, S., ve See, L. (2005). Comparison of land cover maps using fuzzy agreement. International Journal of Geographical Information Science, 19(7), 787-807.
  • GEE. (2025). GEE ESRI 10m annual land cover (2017–2023). Erişim adresi: https://gee-community-catalog.org/projects/S2TSLULC/.
  • Van Genderen, J. L., ve Lock, B. F. (1977). Testing land-use map accuracy. Photogrammetric Engineering and Remote Sensing, 43(9), 1135-1137.
  • Van Genderen, J. L., Lock, B. F., ve Vass, P. A. (1978). Remote sensing: Statistical testing of thematic map accuracy. Remote Sensing of Environment, 7(1), 3-14.
  • Hadi, S. J., Shafri, H. Z. M., ve Mahir, M. D. (2014). Modelling LULC for the period 2010–2030 using GIS and remote sensing: A case study of Tikrit, Iraq. IOP Conference Series: Earth and Environmental Science, 20, 012053.
  • Hassan, M. M., ve Nazem, M. N. I. (2016). Examination of land use/land cover changes, urban growth dynamics, and environmental sustainability in Chittagong City, Bangladesh. Environment, Development and Sustainability, 18(3), 697-716.
  • Karra, K., Kontgis, C., Statman-Weil, Z., Mazzariello, J. C., Mathis, M., ve Brumby, S. P. (2021). Global land use/land cover with Sentinel 2 and deep learning. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (pp. 4704-4707). IEEE.
  • Liping, C., Yujun, S., ve Saeed, S. (2018). Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—A case study of a hilly area, Jiangle, China. PloS One, 13(7), e0200493.
  • Maingi, J. K., Kepner, S. E., & Edmonds, W. G. (2002). Accuracy Assessment of 1992 Landsat-MSS Derived Land Cover for the Upper San Pedro Watershed(US/Mexico). Sponsored by Environmental Protection Agency, Las Vegas, NV. National Exposure Research Lab, 2002.
  • Olofsson, P., Foody, G. M., Stehman, S. V., & Woodcock, C. E. (2013). Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sensing of Environment, 129, 122-131.
  • Rwanga, S. S., ve Ndambuki, J. M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences, 8(4), 611-622.
  • San Miguel-Ayanz, J., & Biging, G. S. (1997). Comparison of single-stage and multi-stage classification approaches for cover type mapping with TM and SPOT data. Remote Sensing of Environment, 59(1), 92-104. Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 62(1), 77-89.
  • Venter, Z. S., Barton, D. N., Chakraborty, T., Simensen, T., ve Singh, G. (2022). Global 10 m land use land cover datasets: A comparison of Dynamic World, WorldCover and Esri land cover. Remote Sensing, 14(16), 4101.
  • Zanaga, D., Van De Kerchove, R., Daems, D., De Keersmaecker, W., Brockmann, C., Kirches, G., Wevers, J., Cartus, O., Santoro, M., ve Fritz, S. (2022). ESA WorldCover 10 m 2021 V200.
There are 21 citations in total.

Details

Primary Language Turkish
Subjects Forestry Management and Environment
Journal Section Research Articles
Authors

Fidan Şevval Bulut 0000-0001-9836-5689

Ayhan Ateşoğlu 0000-0002-4030-7782

Emrah Acar 0009-0002-8941-3882

Early Pub Date August 21, 2025
Publication Date
Submission Date March 27, 2025
Acceptance Date August 12, 2025
Published in Issue Year 2025 Volume: 27 Issue: 2

Cite

APA Bulut, F. Ş., Ateşoğlu, A., & Acar, E. (2025). Türkiye İçin Küresel Arazi Kullanımı/Örtüsü Haritalarının Doğruluğunun Değerlendirilmesi: ESA World Cover ve ESRI Land Cover Karşılaştırması. Bartın Orman Fakültesi Dergisi, 27(2), 223-238. https://doi.org/10.24011/barofd.1666812


Bartin Orman Fakultesi Dergisi Editorship,

Bartin University, Faculty of Forestry, Dean Floor No:106, Agdaci District, 74100 Bartin-Turkey.

Fax: +90 (378) 223 5077, Fax: +90 (378) 223 5062,

E-mail: bofdergi@gmail.com