student from 01.01.2024 until now
Russian Federation
Russian Federation
The article explores the prospects of applying artificial intelligence (AI) technologies to create adaptive microclimate control systems for smart greenhouses in the Republic of Sakha (Yakutia). The relevance of the work is driven by the need to transition from traditional threshold-based control systems to intelligent management, ensuring sustainable agricultural production in this region with its extreme climate. A proprietary architecture for an adaptive system based on a hybrid model (digital twin) and a reinforcement learning algorithm is proposed as a solution. Predictive data on the potential efficiency of such systems are presented, including increased crop yield, energy savings, and significant reductions in water consumption. Key advantages are discussed, alongside implementation challenges such as cost, data requirements, and model interpretability, with proposed pathways to address them. The conclusion is drawn that AI technologies are a key driver for creating autonomous, resource-efficient, and sustainable agricultural systems of the future.
Agriculture, agroclimate, Republic of Sakha (Yakutia artificial intelligence (AI), microclimate, biotechnology, smart greenhouse, internet of Things (IoT), digital twin
1. Mikhailova N.A., Antipov A.V. Automation of a smart greenhouse: development and implementation of a microclimate control system // Science Bulletin No. 3 (84) Volume 1. Pp. 557 - 561. 2025. ISSN 2712-8849 // Electronic resource: https://www.vestnik-nauki.rf/article/21730 (accessed: 11.12.2025)
2. Artificial Intelligence in Agriculture // Weather in the Field. – URL: https://weatherinthefield.rf/iskusstvenniy-intellekt-v-selskom-khozyaystve (accessed: 12.12.2025).
3. Levashkin A. G. Development of a Universal Smart Greenhouse System / A. G. Levashkin, A. V. Malusha // Innovatics-2023: Collection of Materials of the XIX International School-Conference of Students, Postgraduates and Young Scientists, April 21-22, 2023, Tomsk, Russia. Tomsk, 2023. Pp. 50-54. URL: http://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001006161
4. Cherepenin V.A., Katsupcev A.A. Analysis of Approaches to Creating a "Smart Greenhouse" System Based on a Neural Network // Software Systems and Computational Methods. 2024. No. 1. DOI:https://doi.org/10.7256/2454-0714.2024.1.69794 EDN: https://elibrary.ru/XAZVOW URL: https://nbpublish.com/library_read_article.php?id=69794
5. van Os J., et al. Digital Twins in Horticulture: A Review // Computers and Electronics in Agriculture. 2022. Vol. 199. P. 107183.
6. The Future of Indoor Farming: Technology, Economics and Sustainability // BCG Report. 2021. URL: https://www.bcg.com/publications/2021/future-of-indoor-farming (accessed: 12.10.2025).
7. Hemming S., et al. Reinforcement Learning for Climate and Irrigation Control in Greenhouses: A Simulation Study // IFAC-PapersOnLine. 2020. Vol. 53(2). Pp. 16798-16803.
8. Jones H.G. Irrigation Scheduling: Advantages and Pitfalls of Plant-Based Methods // Journal of Experimental Botany. 2004. Vol. 55(407). Pp. 2427-2436.
9. Methodology for Forming the Balance of Food Resources in the Republic of Sakha (Yakutia) Taking into Account Regional Peculiarities: A Methodological Guide / G.I. Dayanova, I.K. Yegorova, L.D. Protopopova, N.N. Nikitina, A.N. Krylova, A.F. Baisheva – Yakutsk: Publishing House "Dyoluo", 2019. – 335 p.
