بررسی و مقایسه میزان دقت نقشه‌های کاربری اراضی حاصل از نرم‌افزار اکاگ نیشن و گوگل ارث انجین (مطالعه موردی: حوزه آبخیز دامغان)

نویسندگان
1 مرکز تحقیقات کشاورزی و منابع طبیعی زنجان، گروه تحقیقات جنگل و مرتع
2 دانشکده کویرشناسی، دانشگاه سمنان
10.22034/wmji.2024.2039506.1086
چکیده
تغییرات کاربری اراضی یکی از پارامترهای اثرگذار بر تغییرات محیط‌زیست جهانی است. این تغییرات بر دامنه‌ای وسیعی از ویژگی‌های محیط‌زیست و منابع طبیعی تأثیرگذار است، بر این اساس بررسی دقت نقشه‌های استخراجی کاربری اراضی جهت مشخص نمودن این تغییرات برای مدیریت بهتر و استفاده مناسب‌تر از حوزه­های آبخیز از اهمیت ویژه‌ای برخوردار است. هدف این پژوهش تعیین و بررسی روش‌های با دقت بالا جهت استخراج نقشه‌های کاربری اراضی برای بخشی از حوزه آبخیز دامغان بوده است. بدین منظور ابتدا نقشه‌های کاربری منطقه با استفاده از پردازش تصاویر ماهواره لندست 8، نرم‌افزارهای اکاگ نیشن و سامانه گوگل ارث انجین برای سال 2020 تهیه شد. سپس با استفاده از شاخص‌های ضریب کاپا، ضریب دقت کلی و دقت کاربر بر اساس مطالعات میدانی در 100 نقطه تصادفی، تصاویر گوگل ارث و اطلاعات طرح تفضیلی-اجرایی انجام‌شده در منطقه، دقت نقشه­های حاصل بررسی شد. نتایج نشان داد که ضریب کاپا و دقت کلی برای نقشه‌های حاصل از نرم‌افزار اکاگ نیشن به ترتیب برابر 94/0 و 95/0 و برای گوگل ارث انجین 0/66 و 0/73 است؛ بر این اساس نقشه‌ کاربری اراضی تهیه‌شده برای حوزه آبخیز دامغان با استفاده از اکاگ نیشن دقت بالاتری را نشان می‌دهد. لذا در مناطقی با مساحت در حدود منطقه موردمطالعه یا کم‌تر برای مطالعه و بررسی تغییرات کاربری اراضی بهتر است به‌جای سامانه گوگل ارث انجین از سایر نرم‌افزارهای سنجش‌ازدور ازجمله اکاگ نیشن که نقشه ­هایی با دقت بالاتر و انطباق بیش‌تر با کاربری­ های اراضی تولید می­کنند، استفاده شود.
کلیدواژه‌ها

عنوان مقاله English

Investigation and comparison of the accuracy of land use maps obtained from eCognition software and Google Earth Engine (case study of Damghan watershed)

نویسندگان English

Peyman Akbarzadeh 1
Shima Nikoo 2
1 Zanjan Agriculture and Natural Resources Research Center, Forest and Pasture Research Department
2 , Faculty of Desert Studies, Semnan University
چکیده English

Land use changes are one of the parameters affecting global environmental changes. These changes affect a wide range of environmental features and natural resources, etc., based on this, it is of particular importance to check the accuracy of land use extraction maps to determine these changes for better management and more appropriate use of watersheds. The purpose of this research was to determine and examine high-precision methods for extracting land use maps for a part of the Damghan watershed. For this purpose, the user maps of the region were prepared using Landsat 8 satellite image processing, eCognition software and Google Earth Engine system for 2020.Then, the accuracy of the resulting maps was checked using Kappa coefficient, overall accuracy coefficient and user accuracy based on field studies in 100 random points, Google Earth images and information on the implementation plan carried out in the region. The results showed that the Kappa coefficient and the overall accuracy for the maps obtained from eCognition software are 0.94 and 0.95, respectively, and for Google Earth Engine 0.66 and 0.73; Based on this, the land use map prepared for the Damghan watershed using eCognition shows higher accuracy. Therefore, in areas with an area around the study area or less, to study and investigate land use changes It is better to use other remote sensing softwares, such as eCognition, which produce maps with higher accuracy and greater adaptation to land uses, instead of Google Earth Engine.

کلیدواژه‌ها English

Iran Central desert
map efficiency
Object-oriented classification method
Remote sensing
  1. Agarwal, C., Green, G., Grove, J., Evans, T., and Schweik, C. 2001. A review and assessment of land-use change models: Dynamics of space, time, and human choice. Washington, D.C.: U.S. Department of Agriculture.
  2. Akbarzadeh, P. 2022. Identification and analysis of land use and vegetation changes in Damghan watershed. Ph.D. Thesis. Semnan University (In Persian)
  3. Binal, A., Christiana, P.S., and Dhinwab, A. 2018. Long term monitoring and assessment of desertification processes using medium & highresolution satellite data. Applied Geography, 97: 10–24.
  4. Briassoulis, H. 2000. Analysis of Land use change: Theoretical and modeling approaches. Morgantown: West Virginia University.
  5. Durkeh, D. 2018. Quantification of structural changes of dense forest patches from the perspective of the land surface (case study; Southeast forests of Kermanshah province). Master's thesis. Malayer University (In Persian)
  6. Ghafari, S., Moradi, H.R., and Modarres, R. 2018. Comparison of object-oriented and pixel-based classification methods for land use mapping (Case study: Isfahan-Borkhar, Najafabad and Chadeganplains). Journal of RS and GIS for Natural Resources, 7(10): 40-57 (In Persian)
  7. Goldblatt, R., You, W., Hanson, G., and Khandelwal, A.K. 2016. Detecting the boundaries of urban areas in india: A dataset for pixel-based image classification in google earth engine. Remote Sensing, 8(8): 634.
  8. Harciníková, T., and Stankova, H. 2014. The possibilities to support ZB GIS® database update using object-based image analysis in eCognition developer software. Geodesy and Cartography, 40(3): 122-132.
  9. Kakehmami, A., Ghorbani, A., Moameri, M., and Ghafari, S. 2021. Evaluation of land use changes in Ardabil province using satellite image processing. Iranian Journal of Range and Desert Research, 28(3): 537-550 (In Persian)
  10. Khazaee, M., Zare, M., Mokhtari, M. H., Rashtian, A., and Arabi Aliabad, F. 2019. Comparison of Different Classification Methods in Terms of Accuracy for Land Use Mapping: A Case Study of the City of Yazd. The Journal of Geographical Research on Desert Areas, 7(1): 165-178 (In Persian)
  11. Kouassi, J., Amos, G., Lucien, D., Yeboi, B., and Kouamé, CH. 2021. Assessing Land Use and Land Cover Change and Farmers’ Perceptions of Deforestation and Land Degradation in South-West Côte d’Ivoire, West Africa. Land, 10(4): 429.
  12. Lambin, E., Rounsevell, M., and Geist, H. 2000. Are agricultural land-use models able to predict changes in land-use intensity? Agriculture, Ecosystems & Environment, 82: 321- 331.
  13. Lu, D., Mausel, P., Brondizio, E., and Moran, E. 2004. Change detection techniques. International Journal of Remote Sensing, 25(12): 2365-2401.
  14. Mackie, R.I. 2020. Dynamic analysis of structures on multicore computers – Achieving efficiency through objectoriented design. Advances in Engineering Software, 66: 3-9.
  15. Mertens, B., and Lambin, E.F. 2000. Land-Cover-Change Trajectories in Southern Cameroon. Annals of the Association of American Geographers, 90(3): 467-494.
  16. Omidpour, R., Moradi, H.R., and Arkhi, P. 2012. Comparison of basic and object-oriented pixel classification methods in the preparation of land use maps using satellite data. Iranian Journal of Remote Sensing and GIS, 5(3): 99-110 (In Persian)
  17. Rana, M., and Kharel, S. 2019. Feature extraction for urban and agricultural domains using eCognition developer. International Archives of the Photogrammetry. Remote Sensing & Spatial Information Sciences, XLII-3/W6: 609-615.
  18. Schneider, A., Friedl, M.A., and Potere, D. 2010. Mapping global urban areas using MODIS 500-m data: New methods and datasets based on ‘urban Ecoregions’. Remote Sensing of Environment, 114(8): 1733-1746.
  19. Seto, K.C., Fragkias M., Güneralp, B., and Reilly, M.K. 2011. A meta-analysis of global urban land expansion. PloS one, 6(8): e23777.
  20. Sharifipour, M., Soleimani, K., and Shabani, M. 2018. Classification and review of different land use change evaluation models, a case study of the central part of Azadshahr city. International Conference on Agricultural Sciences, Environment, Urban and Rural Development. Payam Noor University, International Center of Georgia, Tbilisi.
  21. Shayesteh, K., and Gharibi, S. 2022. Application of GEE in Dust Actual Sources Detection using Sentinel- 5 and Modis. Journal of Natural Environmental Hazards, 11(34): 1-16 (In Persian)
  22. Shelestov A., Lavreniuk M., Kussul, N., Novikov, A., and Skakun, S. 2017. Exploring Google Earth Engine platform for big data processing: Classification of multi-temporal satellite imagery for crop mapping. Frontiers in Earth Science, 5(7): 1-17.
  23. Soltani, N., and Mohammadnejad, V. 2021. Efficiency of Google Earth Engine (GEE) system in land use change assessment and predicting it using CA-Markov model (Case study of Urmia plain). Journal of RS and GIS for Natural Resources, 12(3):101-114 (In Persian)
  24. Sun, Z., Guo, H., Li, X., Lu, L., and Du, X. 2011. Estimating urban impervious surfaces from Landsat-5 TM imagery using multilayer perceptron neural network and support vector machine. Journal of Applied Remote Sensing, 5(1): 053501.
  25. Sun, Z., Xu, R., Du, W., Wang, L., and Lu, D. 2019. High-resolution urban land mapping in China from sentinel 1A/2 imagery based on Google Earth Engine. Remote Sensing, 11(7): 752.
  26. Sundarakumar, K., Harika, M., Begum, S.A., Yamini, S., and Balakrishna, K. 2012. Land Use and Land Cover Change Detection and Urban Sprawl Analysis of Vijayawada City Using a Landsat Data. Engineering Science & Technology, 4: 170-178.
  27. Veldkamp, A., and Lambin, E.F. 2001. Predicting land-use change. Agriculture, Ecosystems& Environment, 85(1-3): 1-6.
  28. Zhao, Sh., Peng, Ch., Jiang, H.,Tian, D., Lei, X., and Zhou, X. 2006. Land use change in Asia and the ecological consequences. ECOLOGICAL RESEARCH, 21(6): 890-896.
  29. Zhang, W., and Li, H. 2016. Characterizing and Assessing the Agricultural Land Use Intensity of the Beijing Mountainous Region. Sustainability, 8: 1180.