Article · Bulletin of the National Engineering Academy of the Republic of Kazakhstan · June 30, 2026

Application of machine learning algorithms for predicting crop yields

A. Batyrkhanov, Y. Nurmakhanov, D. Kydyrali, S.M. Issayev, Botagoz Zhussipbek, Sveta Toxanova

Abstract

This article examines the potential of using satellite remote sensing data and geographic information systems for the early assessment of agricultural crop yields. During the study, vegetation indices were calculated based on multispectral satellite imagery, and their relationship with actual crop yield was analyzed. Currently, climate change and the limited availability of natural resources require the implementation of new technologies in the agricultural sector. In this regard, Sentinel-2 and Landsat satellite imagery were used to calculate vegetation indices and analyze their relationship with crop productivity. The ArcGIS platform was used for spatial data processing, and the obtained indicators were modeled using machine learning algorithms. Yield prediction was carried out using Random Forest and XGBoost methods, and the accuracy of the models was evaluated using statistical metrics. The results of the study demonstrated that the use of satellite data makes it possible to predict crop yields in advance and support effective decision-making in agriculture. The proposed approach plays an important role in the digitalization of the agro-industrial complex.

Remote Sensing in AgricultureSmart Agriculture and AIClimate change impacts on agriculturecrop yield predictionvegetation indicesSentinel-2

Application of machine learning algorithms for predicting crop yields

Abstract

More by Sagi Issayev