Automatic Classification of Agricultural Crops Using Sentinel-2 Data in the Rainfed Zone of Southern Kazakhstan
Arystanov A. Sagin J. Karabkina N. Arystanova R. Yermekov F. Kabzhanova G. Bekseitova R. Aktymbayeva A. Kutymova N.
September 2025Multidisciplinary Digital Publishing Institute (MDPI)
Agronomy
2025#15Issue 9
Satellite monitoring of agricultural crops plays a crucial role in ensuring food security and in the sustainable management of agricultural resources, particularly in regions dominated by rainfed farming, such as the Turkestan region of Kazakhstan. Many satellite monitoring tasks rely on remote identification of different types of cultivated crops. In developing the proposed method, we accounted for the temporal characteristics of crop growth and development in various climatic zones of rainfed agriculture, analyzed the dynamics of the Normalized Difference Vegetation Index (NDVI) together with ground-based data, and identified effective time periods and patterns for successful crop recognition. This study aims to develop and comparatively assess two methods for the automatic identification of cultivated crops in rainfed zones using Sentinel-2 satellite data for the years 2018 and 2022. The first method is based on detailed classification of pre-digitized field boundaries, providing high accuracy in satellite-based mapping. The second method represents a fully automated approach applied to large rainfed areas, emphasizing operational efficiency and scalability. The results obtained from both methods were validated against official national statistics, ground-based field surveys, and farm-level data. The findings indicate that the field-boundary-based method delivers significantly higher accuracy (average accuracy of 91.1%). While the automated rainfed-zone approach demonstrates lower accuracy (78%), it still produces acceptable results for large-scale monitoring, confirming its suitability for rapid assessment of sown areas. This research highlights the trade-off between the accuracy achieved through detailed field boundary digitization and the efficiency provided by an automated, scalable approach, offering valuable tools for agricultural production management.
agro-climatic zoning , pasture , rainfed zone , spring crops , vegetation indices , winter wheat
Text of the article Перейти на текст статьи
Faculty of Geography and Environmental Sciences, Al-Farabi Kazakh National University, 71 al-Farabi, Almaty, 050040, Kazakhstan
School of Information Technology and Engineering (SITE), Kazakh British Technical University, Almaty, 050005, Kazakhstan
Department of Geological and Environmental Sciences, Western Michigan University, Kalamazoo, 49008, MI, United States
Scientific-Educational and Technological Platform, Kazakh National Agrarian Research University, Almaty, 050010, Kazakhstan
JSC “NC “Kazakhstan Gharysh Sapary”, Turan Ave. 89, Astana, 010000, Kazakhstan
Faculty of Geography and Environmental Sciences
School of Information Technology and Engineering (SITE)
Department of Geological and Environmental Sciences
Scientific-Educational and Technological Platform
JSC “NC “Kazakhstan Gharysh Sapary”
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026