NDVI Eşik Değerleri ve Google Eart Engine Kullanılarak Buğday ve Arpa Yetiştirilen Alanların Belirlenmesi

Abstract

Bu çalışma, Sentinel-2 uydu görüntüleri ve NDVI tabanlı eşik değerler kullanılarak (Aralık 2018-Haziran 2019) buğday ve arpa (B-A) ekim alanlarının tespiti için en uygun görüntüleme zamanını belirlemeyi amaçlamaktadır. Çalışma, Türkiye’nin Çanakkale iline bağlı Mahmudiye köyünde gerçekleştirilmiştir. Rastgele seçilen parseller (RSP), arazi çalışmaları ile belirlenmiş ve aylık en düşük ve en yüksek NDVI eşik değerleri (NDVI en düşük ve NDVI en yüksek) elde edilmiştir. Bu eşik değerler kullanılarak her ay için B-A alanı tahmin haritaları üretilmiştir. Ayrıca, tüm aylara ait eşik koşullarını aynı anda sağlayan alanlar da haritalandırılmıştır. Tahmin edilen ve gerçek B-A alan envanter değerleri karşılaştırılarak yetiştirme sezonu içinde en uygun görüntüleme zamanı belirlenmiştir. Bulgular, Nisan ayında elde edilen görüntünün kullanımının, sadece 53 piksel fazla tahmin ile en tatmin edici B-A alanı tahminini verdiğini göstermiştir. Benzer iklim koşulları altında, arazi kullanım ve arazi örtüsü sınıflama metotlarına göre daha zaman- ve emek efektif incelemeler sağlayan NDVI en düşük ve NDVI en yüksek eşikleri metodu göz önüne alınarak B-A yetiştirilen alan ve verim tahminlemelerinde, daha hassas tahmin eldesi için Nisan ayında alınan görüntülerin kullanımı önerilmektedir.

Keywords

• Buğday-Arpa
• GEE
• görüntüleme zamanı
• NDVI eşik değer
• Sentinel-2

Wheat and Barley Cultivated Area Determination Using NDVI Threshold Values and Google Earth Engine

Abstract

This study aims to determine the optimal imaging time for detecting wheat and barley (W-B) cultivated areas using Sentinel-2 images and NDVI-based threshold values (December 2018-June 2019) via Google Earth Engine (GEE). The study was conducted in Mahmudiye village, situated to Çanakkale province, Türkiye. Randomly selected parcels (RSP) were determined through ground surveys were used to obtain monthly minimum and maximum NDVI thresholds (NDVImin and NDVImax). Monthly NDVI threshold-based W-B maps were produced. In addition to the month-based maps, the areas that meet all the threshold conditions for all months at once were also mapped. The predicted and actual inventory of W-B areas were compared for identification of the most appropriate imaging time within the growing season. Findings have shown that using the image acquired in April gave the most satisfactory W-B area prediction with an overestimation of only 53 pixels. Use of NDVImin and NDVImax thresholds for prediction of W-B cultivated areas and yield predictions considering imageries acquired in April strongly suggested for more precise estimations under similar climate conditions, whereby the method provides more time and labor-effective investigations in comparison with land use land cover classification methods.

Keywords

• GEE
• imaging time
• NDVI threshold values
• Sentinel-2
• Wheat-Barley

References

1. Aghlmand, M., Kalkan, K., Onur, M. I., Öztürk, G., & Ulutak, E. (2021). Google Earth Engine ile arazi kullanımı haritalarının üretimi. Ömer Halisdemir University Journal of Engineering Sciences, 10(1), 038-047. https://doi.org/10.28948/ngumuh.795977 Ayub, M., Khan, N. A., & Haider, R. Z. (2022). Wheat crop field and yield prediction using remote sensing and machine learning. 2nd IEEE International Conference on Artificial Intelligence (ICAI), March 30-31, 2021, Islamabad, Pakistan.
2. Balambar,S., Karimi, Z. K., Öztürk, F., & Acet, Ş. B. (2021). Monitoring agricultural activities by using remote sensing techniques. GSI Journals Series C: Advancements in Information Sciences and Technologies, 4, 58-79.
3. Cavalaris, C., Megoudi, S., Maxouri, M., Anatolitis, K., Sifakis, M., Levizou, E., & Kyparissis, A. (2021). Modeling of durum winter wheat yield based on sentinel-2 imagery. Agronomy, 11(8). https://doi.org/10.3390/agronomy11081486
4. Cheng, E., Zhang, B., Peng, D., Zhong, L., Yu, L., Liu, Y., Xiao, C., Li, C., Li, X., Chen, Y., Ye, H., Wang, H., Yu, R., Hu, J., & Yang, S. (2022). Wheat yield estimation using remote sensing data based on machine learning approaches. Frontiers in Plant Science, 13. https://doi.org/10.3389/fpls.2022.1090970
5. Li, F., Ren, J., Wu, S., Zhao, H., & Zhang, N. (2021). Comparison of regional winter wheat mapping results from different similarity measurement indicators of ndvi time series and their optimized thresholds. Remote Sensing, 13(6). https://doi.org/10.3390/rs13061162
6. Meraj, G., Kanga, S., Ambadkar, A., Kumar, P., Singh, S. K., Farooq, M., Johnson, B. A., Rai, A., & Sahu, N. (2022). Assessing the yield of wheat using satellite remote sensing-based machine. Rouse, J.W., Haas, R.H., Schell, J.A., D.W. (1973). Monitoring vegetation systems in the Great Plains with ERTS. In Proceedings of Third Earth Resources Technology Satellite Symposium, Washington, D. C.: NASA. Goddart Space Flight Center, (1), 309-317. (NASA SP-351).
7. Shin, T., Ko, J., Jeong, S., Kang, J., Lee, K., & Shim, S. (2022). Assimilation of deep learning and machine learning schemes into a remote sensing-incorporated crop model to simulate barley and wheat productivities. Remote Sensing, 14(21). 5443. https://doi.org/10.3390/rs14215443
8. Tian, H., Meng, M., Wu, M., Niu, Z. (2019). Mapping spring canola and spring wheat using Radarsat-2 and Landsat-8 images with Google Earth Engine. Current Science, 116(2), 291-298.

9. Toscano, P., Castrignano, A., Di Gennaro, S. F., Vonella, A. V., Ventrella, D., & Matese, A. (2019). A precision agriculture approach for durum wheat yield assessment using remote sensing data and yield mapping. Agronomy, 9(8). https://doi.org/10.3390/agronomy9080437
10. Wang, C., Zhang, H., Wu, X., Yang, W., Shen, Y., Lu, B., & Wang, J. (2022). AUTS: A novel approach to mapping winter wheat by automatically updating training samples based on NDVI time series. Agriculture (Switzerland), 12(6). https://doi.org/10.3390/agriculture12060817
11. Wang, L., Liu, J., Yang, F., Fu, C., Teng, F., & Gao, J. (2015). Early recognition of winter wheat area based on GF-1 satellite. Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 31(11), 194–201. https://doi.org/10.11975/j.issn.1002-6819.2015.11.028
12. Yang, A., Zhong, B., & Wu, J. (2019). Monitoring winter wheat in Shandong province using Sentinel data and Google Earth Engine platform. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences. https://doi.org/10.1109/XYZ.2019.123456
13. Qiao, K., Zhu, W., Xie, Z., Wu, S., & Li, S. (2024). New three red-edge vegetation index (VI3RE) for crop seasonal LAI prediction using Sentinel-2 data. International Journal of Applied Earth Observation and Geoinformation, 130. https://doi.org/10.1016/j.jag.2024.103894