Management of Natural Ecosystems

Management of Natural Ecosystems

Comparison of Different Satellite Image Classification Algorithms for Land-Use Mapping

Document Type : Original Article

Authors
Mahdi Tazeh 1
Mahla Hasanzadeh 2
Saeideh kalantari 1
1 Associate Professor, Department of Nature Engineering, Faculty of Agriculture and Natural Resources, Ardakan University, Ardakan, Iran.
2 MS Student of desert management and control, Department of Nature Engineering, Faculty of Agriculture & Natural Resources, Ardakan University, Ardakan, Iran.
10.22034/emj.2026.2082654.1146
Abstract
One of the most essential pieces of information required by natural resource managers and decision-makers is land-use maps. The use of satellite data is one of the fastest and most cost-effective methods for producing land-use maps, the value, applicability, and effectiveness of which depend on their accuracy. Considering that various classification algorithms exist; this study examined their performance in supervised classification for land-use mapping. For this purpose, Landsat-9 satellite images of the Golpayegan basin were acquired in 2024. After applying the necessary corrections, the images were processed and classified using six algorithms: Maximum Likelihood, Minimum Distance to Mean, Mahalanobis Distance, Spectral Angle Mapper, Support Vector Machine, and Parallelepiped. Ground truth data were used to determine the classification accuracy of the generated maps. The results showed that the Support Vector Machine (SVM) method achieved the highest accuracy, with an overall accuracy of 94.0% and a Kappa coefficient of 0.85. The other algorithms ranked as follows, with their corresponding overall accuracies and Kappa coefficients: Mahalanobis Distance (89.97% and 0.76), Maximum Likelihood (86.82% and 0.71), Minimum Distance (84.85% and 0.66), Spectral Angle Mapper (62.48% and 0.37), and Parallelepiped (29.46% and 0.18).These findings indicate that selecting an appropriate algorithm not only directly affects the accuracy of class differentiation but also plays a critical role in precise land monitoring, optimal land management, and natural resource planning. Advanced algorithms such as Support Vector Machine allow for the production of accurate and reliable maps, whereas lower-accuracy algorithms are generally more suitable for preliminary analyses.
Keywords
Supervised Classification
Landsat 9 Satellite
Overall Accuracy
Kappa Coefficient
Subjects
ابوترابی، ح.، بهدانی، م.، و وحیدی، م. (1394). مقایسه الگوریتم‌های مختلف طبقه‌بندی تصاویر ماهوارهای در تهیه نقشه کاربری اراضی( مطالعه موردی: شهرستان قاینات). سومین همایش ملی انجمن های علمی دانشجویی رشته های کشاورزی و منابع طبیعی،کرج. اردیبهشت 1394.
جعفری، م.، زهتابیان، غ.، احسانی، ا.، و منبری، س. (1392). استفاده از داده‌های ماهواره لندست، سنجنده ETM+  جهت بررسی وضعیت پوشش سطح زمین (مطالعه موردی: کاشان). تحقیقات مرتع و بیابان ایران، (2)20، 297-285.
شنانی هویزه،س.، و زارعی، ح. (1395). مقایسه الگوریتم‌های طبقه‌بندی شبکه عصبی مصنوعی، ماشین‌بردار پشتیبان و حداکثر احتمال در استخراج نقشه کاربری اراضی حوزه آبخیز ابوالعباس. علوم و مهندسی آبخیزداری ایران، (23)10، 84-73.
فتحی‌زاد، ح.، صفری، ع.، بازگیر، م.، و خسروی. غ. ر. (1395). ارزیابی و مقایسه روش‌های ماشین‌بردار پشتیبان با کرنل‌های خطی، چند جمله‌ای و پایه شعاعی با شبکه عصبی مصنوعی جهت طبقه‌بندی کاربری اراضی. تحقیقات مرتع و بیابان ایران، (4)23، 730-721.
نوروزی، م.، وهاب‌زاده، ق.، سلیمانی، ک.، و شعبانی، م. (1400). مقایسه الگوریتم‌های مختلف طبقه‌بندی تصاویر ماهواره‌ای در تهیه نقشه کاربری اراضی (مطالعه موردی: بخشی از استان مازندران). دومین کنفرانس ملی تغییرات محیطی با استفاده از فناوری سنجش از دور. ساری، اسفند 1400.
یوسفی،ص.، تازه، م.، میرزایی، س.، مرادی، ح.، و توانگر،ش. (1393). مقایسه الگوریتم‌های مختلف طبقه‌بندی تصاویر ماهواره‌ای در تهیه نقشه کاربری اراضی (مطالعه موردی: شهرستان نور). سنجش از دور و سامانه اطلاعات جغرافیایی در منابع طبیعی، (3)5، 76-67.
Abdi, A.M. (2020). Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing, 57(1), 1-20.
Ahirwar, R., Malik, M.S., and Shukla, J.P. (2018). Development of Hybrid Unsupervised Classification Techniques for Accuracy enhancement of Land Use/Land Cover Mapping Using Geo-Spatial Technology: Hoshangabad, District Madhya Pradesh India. Geoinfor Geostat: An Overview, 6(3).
Alhassan, V., Henry, C., Ramanna, S., and Storie, C. (2020). A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery. Neural Computing and Applications, 32, 8529-8544.‏
Chowdhury, M.S. (2024). Comparison of accuracy and reliability of random forest, support vector machine, artificial neural network and maximum likelihood method in land use/cover classification of urban setting. Environmental Challenges, 14, 100800.
Hester, D.B. (2008). Land cover mapping and change detection in urban watersheds using Quickbird high spatial resolution satellite imagery. North Carolina State University. Carolina.
Hu, Y., Dong, Y., and Nacun, B. (2018). An automatic approach for land-change detection and land updates based on integrated NDVI timing analysis and the CVAPS method with GEE support. ISPRS Journal of Photogrammetry and Remote Sensing, 146, 347-359.
Hussain, S., Mubeen, M., Ahmad, A., Akram, W., Hammad, H.M., Ali, M., Masood, N., Amin, A., Farid, H.U., Sultana, S.R., Fahad, S., Wang, D. and Nasim, W. (2020). Using GIS tools to detect the land use/land cover changes during forty years in Lodhran District of Pakistan. Environmental Science and Pollution Research, 27(32), 39676-39692.
Jensen, J.R. (1996). Introductory digital image processing: a remote sensing perspective. New Jersyy: Prentice Hall, 318p.
Kruse, F.A., Lefkoff, A.B., Boardman, J.W., Heidebrecht, K.B., Shapiro, A., Barloon, P.J., and Goetz, A.F. (1993). The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer data. Remote sensing of environment, 44(2-3), 145-163.
Kumar, A., and Gorai, A.K. (2023). Design of an optimized deep learning algorithm for automatic classification of high-resolution satellite dataset (LISS IV) for studying land-use patterns in a mining region. Computers & Geosciences, 170, 105251.
Mountrakis, G., Im, J., and Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247-259.
Oommen, T., Misra, D., Twarakavi, N. K., Prakash, A., Sahoo, B., and Bandopadhyay, S. (2008). An objective analysis of support vector machine-based classification for remote sensing. Mathematical Geosciences, 40(4), 409-424.
Pal, M., and Mather, P.M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007-1011.
Pande, C. B. (2022). Land use/land cover and change detection mapping in Rahuri watershed area (MS), India using the google earth engine and machine learning approach. Geocarto International, 37(26), 13860-13880.
Phan, D.C., Trung, T.H., Truong, V.T., Sasagawa, T., Vu, T.P.T., Bui, D.T., Hayashi, M., Tadono, T., and Nasahara, K. N. (2021). First comprehensive quantification of annual land use/cover from 1990 to 2020 across mainland Vietnam. Scientific Reports, 11(1), 9979.
Phiri, D., Morgenroth, J., Xu, C., and Hermosilla, T. (2018). Effects of pre-processing methods on Landsat OLI-8 land cover classification using OBIA and random forests classifier. International Journal of Applied Earth Observation and Geoinformation, 73(6), 170-178.
Richard, J.A. (2006). Remote Sensing Digital Image Analysis, Berlin: Springer-Verlag, 439p.
Szuster, B.W., Chen, Q., and Borger, M. (2011). A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Applied Geography, 31(2), 525-532.
Wulder, M.A., Coops, N.C., Roy, D.P., White, J.C., and Hermosilla, T. (2018). Land cover 2.0. International Journal of Remote Sensing, 39(12), 4254-4284.
Yimer, S.M., Bouanani, A., Kumar, N., Tischbein, B., and Borgemeister, C. (2024). Comparison of different machine-learning algorithms for land use land cover mapping in a heterogenous landscape over the Eastern Nile river basin, Ethiopia. Advances in Space Research, 74(5), 2180-2199.
Zhang, C., Chen, Y., and Lu, D. (2015). Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery. International Journal of Remote Sensing, 36(17), 4483-4500.
Zhang, Z., Verbeke, L., De Clercq, E., Ou, X., and De Wulf, R. (2007). Vegetation change detection using artificial neural networks with ancillary data in Xishuangbanna, Yunnan Province, China. Chinese Science Bulletin, 52(Suppl 2), 232-243.

  • Receive Date 31 December 2025
  • Revise Date 30 January 2026
  • Accept Date 02 February 2026