Artificial intelligence in agriculture: a comparative scientometric analysis of global and Russian research

E. V. Sokolova¹, M. N. Goncharova¹ , V. A. Blaginin¹ , V. E. Kovalev¹ , V. S . Kukhar² , V. V. Surgaev²

¹ Ural State University of Economics, Ekaterinburg, Russia

² Ural State Agrarian University, Ekaterinburg, Russia

E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Volume 26 No. 8

Date of paper submission: 07.04.2026, date of review: 22.06.2026, date of acceptance: 10.07.2026. 

Published: 08/31/2026

Abstract. The rapid penetration of artificial intelligence technologies into the agro-industrial complex necessitates a systematic understanding of the current research landscape to identify the most promising development directions. The purpose of this study is to conduct a scientometric assessment of research development in the field of artificial intelligence application in agriculture to determine the stage of development of the direction, identify key thematic clusters, promising technologies, and features of the Russian scientific landscape. Methods. The study was carried out on the basis of a two-stage scientometric analysis. At the first stage, an international sample of publications from the Scopus database (2010–2026) in the subject area “Agricultural and Biological Sciences” was analyzed using the key terms “artificial intelligence”, “machine learning” and related concepts. At the second stage, an analysis of Russian publications was carried out using the OpenAlex database. Data processing was carried out using Bibliometrix (R package) and VOSviewer software. Results. A logistic model of publication activity growth was constructed, demonstrating that the direction is in the active growth phase with an unrealized potential of about 80 %. The “window of opportunity” for entering the topic was identified – the period 2024–2027. Eleven thematic clusters were identified, covering predictive modeling, machine learning in remote sensing, computer vision for plant disease assessment and livestock monitoring, hyperspectral imaging, as well as the newest areas (generative AI, explainable AI, graph neural networks). The analysis of Russian publications revealed a pragmatic regional orientation: priority is given to accessible machine learning methods for immediate implementation in the agro-industrial complex, forecasting using remote sensing, and risk assessment taking into account geopolitical factors. A lag was revealed in the areas of generative AI in biomolecular research, interpretable AI, computer vision in animal husbandry, and hyperspectral imaging. Scientific novelty. For the first time, a comparative scientometric analysis of global and Russian studies on a unified methodological basis was carried out, identifying the stage of development of the direction, promising technological clusters and features of the national research agenda in the field of AI application in agriculture.

Keywords: artificial intelligence, machine learning, agriculture, scientometric analysis, precision farming, computer vision, remote sensing, generative AI, explainable AI, digitalization of agriculture

For citation: Sokolova E. V., Goncharova M. N., Blaginin V. A., Kovalev V. E., Kukhar V. S., Surgaev V. V. Artificial intelligence in agriculture: a comparative scientometric analysis of global and Russian research. Agrarian Bulletin of the Urals. 2026; 26 (08): 1594‒1608. https://doi.org/10.32417/1997-4868-2026-26-08-1594-1608 (In Russ.)  

 

Download the full text of the article