ADOP 2026

AI-Based Decision Support System for Sustainable Agriculture in Cyprus: Integrating Data Analytics and Resource Optimization

Andrey Leonidovich Ronzhin — 2026-09-24

Agriculture in the Mediterranean regions is exposed to the pressures of climate change, limited water resources and the need for more efficient of production systems. Cyprus represents a relevant example due to the pronounced scarcity of water, the fragmented structure of farms and the significant role of irrigation in crop production. Digital technologies and artificial intelligence can contribute to the development of more efficient decision support systems in sustainable agriculture. This paper proposes a conceptual AI-based decision support system (AI-DSS) for sustainable agriculture in Cyprus, which links the analysis of agricultural data with the logic of resource allocation optimization. The proposed framework is based on publicly available and verified statistical data from the CYSTAT, Eurostat and FAOSTAT databases, while the optimization component is conceptually connected to the General Algebraic Modelling System (GAMS) platform in order to illustrate the possibility of distributing limited water resources within a decision support system.

The research relies on official data on farm structure, land use, irrigation and production of key crops in Cyprus, with a particular focus on potatoes, citrus, grapes and olives as representative crops for analytical and optimization purposes. Analytical scenarios of different levels of water availability were developed to examine how the proposed system could support adaptive planning of agricultural production under conditions of increased resource pressure. The results confirm that Cypriot agriculture combines a small average farm size with a significant dependence of certain crops on irrigation, which makes water distribution one of the key sustainability issues of the sector. The proposed AI-DSS framework shows how official statistical data, analytical processing and optimization-oriented reasoning can be combined into a single structure for decision support.

Hybrid tractor as an energy and digital accelerator for the technical transformation of the agro-industrial complex

kryuchkovv — 2026-09-24

Of the over 5,200 tractors produced annually in Russia, about 90% have more than 220 horsepower and belong to traction class 4 or higher. Notably, 63% of these are powerful machines above 380 hp, made by just two manufacturers – PTZ and Rostselmash. The dominance of such high-powered tractors stems from a historical focus on increasing engine power and energy density, which, by current standards, is considered irrational. This trend inhibits energy efficiency and results in negative environmental and economic impacts. The article proposes a method for utilizing data from information systems installed on tractors to reconstruct a "digital twin" of the field. This approach characterizes the field through its response to tractor-induced disturbances. Using the collected data, researchers derived an equivalent resistance parameter in field coordinates and developed a latent space vector function. Analyzing this function over specific time intervals and distances enables calculation of integral energy expenditures, mapping of field energy consumption, and assessment of work performed relative to distance traveled. A significant outcome is the creation of a generalized functional that accounts for different interaction scenarios, such as atmospheric emissions, supporting real-time or retrospective analysis and optimization of tractor operations with respect to potential control strategies.

Status and prospects of implementing digital technologies for cultivating agricultural crops under the changing climate (using Altai Krai as an example)

Unknown — 2026-09-24

The article presents the evaluating the current adoption and future trajectory of smart farming solutions for crop management amidst shifting climatic patterns in Altai Krai. As evidenced by comprehensive analyses, no crop production system can fully neutralize the impact of weather variability. Examination of the last six solar activity cycles reveals a pronounced upward trend in both mean annual air temperature and total precipitation across the region, accompanied by substantial interannual variability. Notably, over the past six years, a statistically significant shift in precipitation patterns has been observed, with a greater proportion of rainfall occurring toward the end of the growing season and in increased volumes. May exhibits the highest amplitude of fluctuations in both temperature and precipitation. Such climatic instability poses considerable challenges for the timely and high-quality implementation of agronomic operations within optimal technological windows. As a consequence, substantial yield losses and deterioration in grain quality are frequently recorded. When compounded by pronounced volatility in grain markets, these factors markedly elevate the economic risks threatening farm sustainability. This raises a critical question: how can the agroclimatic potential of agricultural enterprises be accurately assessed, and how can an efficient land-use system be established under such conditions? The answer lies in the integration of digital technologies into agricultural management systems. Over recent years, the region has progressively implemented a digital meteorological data service supported by a network of more than 100 in-field soil–weather stations. This infrastructure enables real-time monitoring and analysis of crop growth conditions, facilitates prompt managerial decision-making, and supports the rational design of cropping patterns, crop rotations, and cultivation technologies. In the longer term, it also provides a foundation for predictive modeling of crop production. Concurrently, differentiated application technologies for seeds and fertilizers have been developed and deployed based on prescription maps and field productivity zoning. These approaches ensure the most efficient utilization of the agroclimatic potential of individual field segments and their integrated management units, ultimately enhancing crop productivity. A substantial body of research has focused on optimizing integrated plant nutrition systems incorporating biological products. High efficacy of such biostimulants and biofertilizers has been demonstrated when applied in combination with mineral fertilizers and tailored to field-specific soil fertility zones. Ongoing research also addresses site-specific crop protection strategies, including weed, pest, and disease identification through computer vision technologies. These systems are implemented via both ground-based platforms and unmanned aerial vehicles. The integration of these digital solutions combined with advanced machinery, innovative tillage practices, improved cultivars and seeds, balanced fertilization systems, modern crop protection products, and adequate financial resources creates the conditions necessary to ensure the long-term economic resilience and sustainable development of agricultural enterprises.

Route planning for a robotic platform for applying mineral fertilizers

Aliaksandr A Zheshka — 2026-09-24

The implementation of technological operations for the application of fertilizers and chemical plant protection products is carried out during the cultivation of most crops, and the yield directly depends on the quality of these operations. However, the performance of these works has a negative impact on the environment and the health of people who operate machines for applying fertilizers and chemical plant protection products. In this regard, the intellectualization and robotization of the process of applying fertilizers and chemical plant protection products, which eliminates the presence of a machine operator, is an urgent scientific direction. The use of robotic platforms has a positive economic effect, as it reduces labor costs per unit area of the field, increases the duration of working hours, productivity and quality of fertilizer distribution over the field surface. The coordinate application of specified doses of mineral fertilizers in accordance with the map of nutrients in the soil makes it possible to equalize soil fertility. A promising direction is also the use of robotic machine links, where the main machine is equipped with the most powerful hardware and software base, which allows it to be used to build a map of the work area, taking into account the terrain of the field and vegetation, the other robotic machines working in the same link with the main one receive information about the trajectory from it and in parallel, fertilizers are distributed over the surface of the work area. In this paper, the specifics of planning the route of a robotic platform for the application of mineral fertilizers are considered, and the results of processing point areas obtained during the study of the characteristics of the platform's movement along the work site are presented.

Multi-Channel Mixing System for a UAV Ground Servicing Platform

Andrey Leonidovich Ronzhin — 2026-09-24

The problem of automating the preparation and refueling of liquid chemical solutions for unmanned aerial vehicles used in agricultural spraying is investigated. A review of studies on the application of UAVs for spraying and the types of agricultural crops is provided. The relevance of the research is justified by the need for comprehensive field servicing of agricultural drones, including not only battery replacement but also the automatic refilling of tanks with working solution. A developed multichannel mixing module for an autonomous ground platform is presented, capable of dispensing concentrates with various dilution ratios and mixing them in a water flow. The modular architecture of the mixer includes two types of dispensers (pneumatic for large volumes and syringe-type for small volumes), a unified control unit based on an STM32F103 microcontroller with RS-485 network support, as well as a quick-release collet cap for connecting standard containers. Research is ongoing regarding the analysis of the influence of different concentrate viscosities on dosing accuracy, as well as the automatic formulation of solutions based on agrotechnical prescriptions.

Methodology for operating agricultural UAVs with automatic calibration and semantic layout of flight missions

Artem Ryabinov — 2026-09-24

This paper presents a functional model of a group of unmanned aerial vehicles (UAVs) for liquid fertilizer application, as well as a method for automating the preparation and execution of flight missions formulated as a skill-based system. The first part of the study identifies the primary challenge as high cognitive workload. A model of liquid substance application is then introduced, describing a closed-loop process of planning – task allocation – synchronized execution – monitoring, considering UAV technical constraints and agronomic requirements. The theoretical foundations for mission parameter calculation are examined in detail, including application rate of the working solution, pump performance, flight speed, swath width, and pass overlap percentage. An automatic calibration algorithm for the liquid application system is proposed, in which the ground control station compares theoretical and actual flow parameters and provides a ready-to-use solution. A method for decomposing UAV missions into atomic tasks is proposed, distinguished by their automatic composition into a unified skill based on the semantics of the user request. This approach enables transferring analysis and decision-making functions from the human operator to a computational system. The practical significance of the work lies in simplifying mission preparation, minimizing human-factor errors, and improving the efficiency of cooperative UAV deployment in agricultural applications.

PROSPECTS FOR THE USE OF NATURAL GAS MOTOR FUEL IN AGRICULTURE IN THE CONTEXT OF ENHANCING ENVIRONMENTAL PERFORMANCE AND SUSTAINABLE DEVELOPMENT

chutcheva_30031977 — 2026-09-24

This paper provides a systematic review and critical synthesis of Russian and international studies on the use of natural gas motor fuel (compressed natural gas, CNG, and liquefied natural gas, LNG) in agriculture as a means of reducing operating costs and environmental pressure within the sustainable development agenda. The empirical analysis relies on official Rosstat statistics on the stock of key categories of agricultural machinery in Russia for 2019–2024 and includes the calculation of growth rates and structural ratios. The results indicate a decline in the fleets of tractors, cultivators, and forage harvesters, alongside relative stabilization in the grain harvester segment, suggesting heterogeneous patterns of capital renewal. To assess the potential for technological upgrading, the study proposes a Fleet Technical Readiness Index (0–1) and a scenario-based evaluation of its increase under accelerated renewal supported by preferential leasing and subsidies. Provisions of the Russian Natural Gas Motor Fuel Market Development Concept through 2035 are used to interpret targets for machinery production and infrastructure expansion. The findings show that even limited adoption of natural gas motor fuel in 2024 was associated with a measurable reduction in greenhouse gas emissions and lower fuel expenditures, confirming the climatic and economic relevance of this pathway. Key scaling barriers include infrastructure constraints in agricultural regions, the need for qualified maintenance, and risks related to component dependence and methane leakage along the supply chain.

Оperator's server development for controlling the movement of a robotic platform

Viktor Vladimirovich Goldyban — 2026-09-24

A promising direction for the development of agricultural production is the integrated robotization of crop production processes. This is explained by the reduction of labor resources in agricultural enterprises, the performance of work in conditions of dust and gas pollution, excessive vibration and noise levels, interaction with fertilizers and pesticides, and overtime work during peak periods of crop cultivation. Autonomous agricultural machinery makes it possible to reduce the need for the number of employed operators in crop production, and minimize the negative impact of machinery on humans and the environment. An analysis of literature sources shows that there is currently positive research experience in the use of robotic platforms for fertilization and pesticides, tillage, sowing and planting crops, monitoring and care of crops, and even harvesting. This article examines the оperator's server development for autonomous remote control of a robotic platform. The architecture of a multi-agent control system for the robotic platform is presented. A query typing system is implemented to ensure flexible data exchange between the server and agents. The research was conducted to organize control of the Smouz robotic platform during herbicide treatments of row crops.

Development of a Low-Cost Monocular Vision System for Robotic Grasping of Dairy Bottles on Flexible Conveyor Lines

Ranil Salimov — 2026-09-24

This paper presents a low-cost monocular computer vision system for real-time detection and 3D localization of round objects (dairy bottle caps) on a conveyor belt, designed for robotic grasping by an industrial manipulator KUKA KR-3. The system addresses the challenge of achieving acceptable accuracy with minimal hardware — using only a single RGB camera and one static ArUco calibration marker. The proposed approach consists of two main modules: 1) object detection based on the Hough Gradient Method for precise (x, y) localization in the image plane; 2) monocular metric depth estimation using the Depth Anything V2 foundation model to generate a relative depth map, followed by simple scaling with a single ArUco marker placed on the conveyor. Experimental evaluation on a dataset of 45 image showed a mean absolute error in depth estimation of 1.81 cm. This accuracy level is sufficient for reliable grasping of dairy bottles, as the error is effectively compensated by gripping the object at its central height. The system demonstrates good robustness to typical production conditions, including specular reflections on plastic surfaces and varying illumination. The developed solution offers a cost-effective and easily deployable alternative to expensive stereo or LiDAR-based systems, making it highly suitable for flexible production lines in the dairy and organic food industry. The results confirm the practical applicability of the monocular approach for Industry 4.0 automation in agro-industrial enterprises.

Model-Based Design of a Control System for a Group of Agricultural Drones and a Robotic Swap Station

Mikhail Kuzmenkov — 2026-09-24

This article investigates the principles of designing a control system for a group of agricultural spraying drones and a robotic service station for automatic refueling and battery swap. The system concept is based on a hybrid approach combining elements of centralized and decentralized control: global planning of routes and flight schedules is performed centrally, while local trajectory corrections during flight are permitted at the individual drone level. The response to abnormal (emergency) situations is distributed between central and local control levels. The technical implementation of this concept is expediently realized using a multi-agent architecture that includes drone agents, a service station agent, and an external control agent. The study develops a mathematical framework to quantify drone route deviations, considering both spatial cross-track errors and temporal scheduling offsets. Motion monitoring criteria and admissible deviation limits are introduced, with their exceedance triggering emergency operating modes. Parameters for damping temporal mismatches during approach to the station are defined: for drones arriving ahead of schedule, holding points with battery energy constraints are provided; for delayed drones, a reserved waiting interval between service operations is utilized. A simulation methodology is proposed for validating guidance algorithms and failure criteria at the conceptual design stage. Overall, it is shown that model-oriented design reduces the risk of errors during physical implementation of a complex robotic system and decreases development costs.

Experimental Evaluation of SLAM Performance Under Computational Constraints for Agricultural Indoor Facilities

Elvira Chebotareva — 2026-09-24

The paper considers the problem of implementing a simultaneous localization and mapping (SLAM) system for mobile robots with limited computing resources in an agro-industrial complex. The high cost of industrial navigation solutions makes them economically impractical for automating monitoring tasks in greenhouses, warehouses, and other agricultural facilities characterized by extended geometry and limited lighting. An architecture based on a Raspberry Pi 4 single-board computer, an ESP32 microcontroller and, an LDROBOT LiDAR integrated into the ROS 2 ecosystem is proposed. A comparison of the SLAM Toolbox and Cartographer algorithms was performed, taking into account the computational and thermal limitations of the platform. Experiments in conditions simulating the configuration of extended indoor spaces have shown that the SLAM Toolbox ensures the metric consistency of the map, while Cartographer demonstrates systematic small-scale drift. The resulting system operates in real time with CPU utilization reaching up to 23% and temperatures peaking at 51°C, demonstrating its potential for autonomous monitoring of agricultural facilities without requiring expensive equipment.

Conceptual Multimodal AI Architecture for the Early Diagnosis of Pig Respiratory Diseases

Tatyana Valentinovna Snytnikova — 2026-09-24

This paper explores the development of a conceptual multimodal hardware and software architecture for the early detection of respiratory diseases in pigs at the PMK-3 pig-breeding complex (LLC Pribaltiyskaya Myasnaya Kompaniya Tri). Modern precision livestock farming (PLF) technologies, including acoustic monitoring, computer vision, and infrared thermography, are considered. Existing monomodal approaches are insufficient for effectively automating the process of registering sick animals. Laboratory models are poorly suited to industrial pig farm conditions and do not support integration with ERP systems, including 1C. The proposed architecture is based on edge devices fitted with microphone arrays and thermal imaging cameras. Cascade analysis (an acoustic trigger activates visual and thermal imaging verification) enables highly accurate identification of sick animals, reducing the risk of false alarms and diagnostic delays. The proposed architecture minimizes computing resource consumption and reduces the load on the network infrastructure by transferring only structured metadata to the «1C: Enterprise 8. Livestock Breeding. Pig Farming» ERP system.

Technology of hybrid cattle monitoring using local positioning and video surveillance

Sergey Victorovich Kuleshov — 2026-09-24

The paper discusses the concept of hybrid cattle monitoring based on the integration of local positioning systems (UWB) and intelligent video surveillance. The limitations of traditional observation methods are highlighted, and the effectiveness of a combined approach to improve the accuracy of tracking an object's location within a frame, as well as monitoring animal behavior and physiological state, is substantiated. Methods for synchronizing data from positioning sensors and video analytics are described, along with the possibilities of using this approach to automate zootechnical processes and enable early diagnosis of cattle diseases.

An Automated Tool for Generating Monitoring Models for Complex Agrobiotechnical Systems

Unknown — 2026-09-24

This paper presents an implementation of an algorithm for the automatic structural-parametric synthesis of domain-specific models based on a modified genetic algorithm. The YOLO (You Only Look Once) architecture is used as the core framework, enabling high-speed image analysis on mobile devices. The proposed approach provides agricultural specialists with a tool for independently creating and deploying models and software solutions by uploading appropriate datasets to the AutoGenNet system for automatic neural network generation, without the involvement of machine learning experts. Verification and validation of the developed software were performed on a binary classification task using the example of vegetable crop condition assessment. The computational complexity of the proposed algorithm enables real-time evaluation of the state of a given class of objects.

Dynamic Configuration in Cognitive Cyber-Agriculture Using Multi-Aspect Ontology

Tatiana Levashova — 2026-09-24

The transition to Agriculture 5.0 led to the emergence of cognitive cyber-agricultural systems (CCASs) that incorporate human intelligence into the digital framework to create intelligent, adaptive, and efficient farming. This paper introduces a conceptual model for configuration of a CCAS supported by the mechanism of multi-aspect ontologies. The model offers a way to adapt CCAS behavior to an ever-changing environment through reconfiguration. The multi-aspect ontology integrates heterogeneous aspects representing multiple domain knowledge. These aspects provide reusable methods that can be employed for solving the dynamic configuration problem. The multi-aspect ontology mechanism provides interoperability for independent aspects represented using their internal formalisms, while also capturing the knowledge related to the CCAS configuration problem. With respect to the dynamic configuration problem, the ontology incorporates the aspects of CCAS, dynamic configuration, plan, human-machine team, decision support, profile, and context. An example from first-mile agriculture logistics—in which a human-machine team dynamically configures a CCAS—illustrates the key ideas introduced in the paper. This example demonstrates that the proposed model can be used to solve crucial problems in various agricultural scenarios related to dynamic configuration.

Application of modular Retrieval-Augmented Generation system to support agricultural decision-making

Vladislav Viktorovich Skripnik — 2026-09-24

The paper examines the application of the Retrieval-Augmented Generation (RAG) architecture for intelligent decision support in agriculture. A modular RAG system is proposed that takes into account the complex structure of agricultural knowledge and provides higher relevance of the extracted information compared to naive approaches. The system architecture, methods for improving search quality, as well as practical scenarios are described.

Design and Experimental Evaluation of a Voice Control System for Autonomous Robotic Agricultural Systems

Timur Rimovich Yagafarov — 2026-09-24

This paper presents a multilingual voice control system for autonomous agricultural machinery, addressing the need for intuitive human–machine interfaces in precision farming. The proposed architecture integrates audio capture with a configurable speech recognition module based on Faster Whisper, which transcribes commands and optionally translates from one language to another. Recognized text is processed by a hybrid natural language understanding pipeline combining intent-and-slot-filling models (BERT/T5), and a local large language model (Qwen) for commands of varying complexity. Experimental evaluation shows that medium-sized Whisper models maintain 85–90% accuracy under noise levels up to 13 dBFS, while tiny and base models degrade significantly. The Russian-to-English translation capability of medium models yields satisfactory results without fine-tuning. In the NLP stage, BERT with T5-based error correction achieves 92.7% correct command recognition at 12% Word Error Rate, while a 14B-parameter LLM reaches 96.3% accuracy at higher computational cost. Performance measurements on CPU with INT8 quantization confirm feasibility for resource-constrained edge devices. The proposed solution offers a flexible trade-off between accuracy, latency, and memory consumption, making it suitable for real-world agricultural environments with variable noise levels and mixed-language operators.

IoT-Enabled Smart Packaging for Real-Time Freshness Monitoring of Processed Foods

rahulkamble — 2026-09-24

Smart packaging combines sensor technology and connectivity to actively track food quality, aiming to extend shelf life and reduce waste. We propose and survey an IoT-based system that uses carbon dioxide (CO₂) and ethylene gas sensors integrated into food packaging, communicating data via a microcontroller running Python. The system continuously monitors gas levels (along with temperature/humidity), processes the data (potentially with a machine-learning model), and alerts consumers via a smartphone app when freshness declines. Technical review of CO₂ and ethylene sensor modules (e.g. NDIR CO₂ sensors and electrochemical ethylene sensors) shows they can detect spoilage-related gases at relevant levels (hundreds to thousands of ppm for CO₂; tens of ppm for ethylene). We detail an architecture: sensors → Raspberry Pi (running Python scripts for data acquisition, MQTT communication, and ML inference) → cloud backend → mobile alerts. Experiments on sample perishable items demonstrate that this IoT-enabled smart packaging can predict spoilage and send timely alerts, empowering consumers and retailers to act before food goes bad. With user-friendly APIs and open-source libraries (e.g. Paho-MQTT, Flask, scikit-learn), the system is designed to be low-cost and extensible. In summary, the proposed smart packaging prototype leverages inexpensive sensors and Python-driven analytics to make “breakfast safe and hassle-free” (literally) – ensuring that food stays fresher longer.

Computer Vision for Precision Orchard Inventory: Tree Detection and Planting Density Mapping

alexeykutyrev — 2026-09-24

This article presents a comprehensive method for the automated inventory of intensive industrial orchards using computer vision. The study aims to develop and validate an integrated software solution based on the state-of-the-art YOLO26 deep learning model for counting tree trunks and trellis posts, as well as for spatial analysis of planting density and distribution uniformity. As part of the research, the YOLO26 architecture was adapted (transfer learning), and a specialized dataset reflecting commercial orchard conditions was assembled and annotated. Primary data were collected using a ground robotic platform equipped with a DJI Action 5 Pro camera and a high-precision RTK-GNSS receiver for positioning and georeferencing. The developed software not only performs object detection but also conducts statistical analysis, visualizes spatial distribution, and generates orchard status maps. Experimental testing on a model plot confirmed the system's effectiveness. The YOLO26 Medium model demonstrated a precision of 0.919 and a recall of 0.846. The software revealed an overall tree deficit of 4.95% compared to the target and a statistically significant non-uniformity in their spatial distribution, automatically identifying zones with reduced planting density. The developed system automates labor-intensive monitoring and provides an objective foundation for agronomic decision-making.

Formation of Seasonal Vegetation Index Time Series for Information Support of Cropland Monitoring

Alexey Sergeevich Stepanov — 2026-09-24

Seasonal time series of vegetation indices derived from remote sensing data play an important role in precision agriculture: they are used to study the growth dynamics and condition of crops, forecast yields, and identify crops. Time series formed from optical and radar satellite data, as well as UAV data, often require additional processing to eliminate gaps and enable the calculation of daily values. This article describes the principles of forming seasonal VI series using nonlinear approximating functions. Sentinel-2 and Landsat-8/9 data from 2022 to 2024, Sentinel-1 data from 2021, and monthly DJI Mavic 3M imagery from 2024 were used to assess the fitting accuracy of NDVI and DpRVI series using the following functions: linear combination of Gaussian functions (DG); linear combination of sines (DS); Fourier series (DF); linear combination of logistic functions (DL). Three classes of cropland in the Khabarovsk Krai were considered: soybean, grain crops, and fallow land. It was revealed that for NDVI curves obtained from Sentinel-2 and Landsat-8/9 data, the fitting accuracy based on DF is significantly higher than when using other functions. The approximation of NDVI value series obtained from DJI Mavic 3M data and DpRVI from Sentinel-1 data is possible with various functions with equal accuracy. The average MAPE for the three classes based on Sentinel-2 and Landsat-8/9 data was 14.2% and 7.8%, based on Sentinel-1 data – 12.6%, and based on DJI Mavic 3M data – 7.1%. Based on the results of DF approximation, the main parameters of reference curves for the seasonal progression of NDVI and DpRVI were constructed and determined. It was revealed that the DOY_max values for soybean crops significantly differed from the corresponding indicators for grain crops and fallow land according to optical and radar data. Using the proposed approach to create seasonal time series is one of the elements of automated continuous digital monitoring of arable lands.

Development of a Robotic Platform for Pollination of Garden Strawberry in City-Farm Conditions Using Neural Network Object Detection

- solovey66 — 2026-09-24

Effective pollination represents a critical biotic constraint in the cultivation of garden strawberry (Fragaria × ananassa Duch.) in vertical city farms. Traditional pollination methods demonstrate low efficiency or are impractical under multi-tier protected cultivation structures. This study presents the concept of a robotic platform equipped with an integrated computer vision system based on a neural network for autonomous detection of strawberry inflorescences and their mechanical pollination. A specialized image dataset of strawberry inflorescences was compiled to train the detection model, ensuring reliable target recognition under real greenhouse lighting conditions characterized by a dual-peak red–blue spectrum and dense plant arrangement. A manipulator prototype was developed, incorporating a 3D-printed frame, stepper motors, and a control board with an embedded neural processing unit (NPU). The proposed design is expected to provide precise positioning of the end effector and gentle interaction with inflorescence. The modular architecture of the platform enables adaptation to other crops and additional agricultural tasks. The developed solution establishes a foundation for the implementation of automated pollination technologies in protected cultivation within the framework of digital transformation of the agro-industrial sector.

Real-Time CNN-Based Detection System for an Autonomous Agricultural Robot in Open-Field Conditions

Evgenii Mitrofanov — 2026-09-24

The automation of weed control is critical for precision agriculture, yet its implementation on autonomous field robots faces significant challenges due to limited onboard computational resources and dynamic environmental conditions. This study presents the development and evaluation of a real-time computer vision system for an autonomous agricultural robot (agrobot) designed for precision crop monitoring. The proposed system employs an "inverted" detection strategy, where a neural network identifies target crop plants (tobacco) to allow for the subsequent localization of weeds as undetected green mass. The hardware platform is centered on the energy-efficient NVIDIA Jetson Orin Nano, integrated with a GNSS RTK receiver for centimeter-level geotagging, all orchestrated within a ROS 2 framework. To identify an optimal balance between detection accuracy and inference speed under severe hardware constraints, a comparative analysis of various convolutional neural network (CNN) architectures, including YOLOv5 and YOLOv8 variants, was conducted. Experimental results demonstrated that while larger models like YOLOv8x offered higher theoretical accuracy (mAP@0.5 0.86), their inference time (97 ms) was prohibitive for real-time operation. The YOLOv8m model was identified as the optimal compromise, achieving a high frame rate (18 FPS, 55.6 ms inference) with robust detection quality (mAP@0.5 0.84, Recall 0.79). This performance enables the robot to process a continuous video stream at speeds up to 2 m/s, generating precise, georeferenced maps of crop locations. The trained model's efficacy was validated on field data, confirming the system's practical viability for guiding targeted interventions and contributing to significant reductions in herbicide use. The study demonstrates a scalable and efficient approach for deploying sophisticated AI on embedded hardware for precision agriculture.

Field Trials of UAVs for Pesticide Treatments to Control Weed Vegetation on Agricultural Lands

Artem Ryabinov — 2026-09-24

This study presents the results of field experiments aimed at evaluating the effectiveness of unmanned aerial vehicles (UAVs) for broadcast herbicide applications to control weed vegetation on agricultural lands. The experiment was conducted in 2025 in the Northwestern region of the Russia on plots previously used for agricultural production, after the harvest of spring (2 ha) and winter (1 ha) crops, characterized by a high degree of infestation with annual and perennial weed species. The systemic herbicide Tornado 540, containing glyphosate (potassium salt) at a concentration of 540 g/L as the active ingredient, was used as the treatment agent. It was established that the use of UAVs achieves a phytotoxic effect comparable to the classical method, while the high concentration of the preparation caused no damage to crop plants. Fourteen days after treatment, the weed vegetation was eliminated, confirming the high biological efficacy of the method. Additionally, the absence of mechanical impact on the soil cover was noted, as well as the possibility of performing agricultural operations under conditions of high soil moisture, where the use of wheeled machinery is impossible due to the risk of soil compaction and structure damage. The obtained data demonstrates the technological, economic, and environmental feasibility of integrating UAVs into the practice of pre-sowing chemical treatment of lands.

Intelligent Early Warning System for Basil Disease Detection in Vertical Farming Using Deep Learning and Morphological Analysis

skudinma — 2026-09-24

This paper presents the results of the development and validation of a prototype intelligent early warning system for plant diseases in vertical farming, using basil (Ocimum basilicum L.) as a model organism. The system integrates computer vision (deep learning) methods with morphological analysis. Experiments were conducted under controlled conditions in a vertical farm with LED lighting using the cultivars "Queen Sheba", "Siamese Queen", and "Kapriz". A YOLOv8x model was trained for trichome detection on leaves (mAP@0.5 = 0.833), revealing a dependence of trichome count on the spectral composition of light (maximum under increased blue-light fraction) and statistically significant differences between adaxial and abaxial leaf surfaces (Mann–Whitney test, p < 0.05). A YOLOv11 model was trained for disease identification (fusarium wilt, bacterial spot) on a dataset of 214 annotated images, achieving a precision of 74.7% at a recall of 69.3%. A morphological analysis module based on the PlantCV library was developed, enabling automatic determination of leaf geometric dimensions with an error of 5–20% depending on imaging conditions; a calibration method using a reference object (pot) was proposed, ensuring independence from camera technical specifications. The technical design of an early warning system integrating visual symptom detection and morphometric monitoring was formulated. The results demonstrate the promising application of neural network technologies for precision monitoring of phytopathologies in vertical greenhouses.

Solar-powered robotic irrigation systems for agricultural crops: analysis and economic efficiency

Alexey Melnikov — 2026-09-24

Climate change and the increasing frequency of droughts are heightening the relevance of employing irrigation systems, a practice simultaneously constrained by the growing scarcity of freshwater resources. Common sprinkler systems, in their current form, perform virtually no other functions, despite their potential to provide a structural framework and energy source for various precision agriculture technologies, such as machine vision systems and manipulators. This article reviews contemporary methods of crop irrigation, including both traditional and automated systems used in agriculture. The advantages of utilizing robotic systems powered by renewable energy sources for irrigation and the execution of associated agrotechnical operations are analyzed. An overview of existing robotic solutions, their design features, and areas of application is provided. The authors propose an original concept for a robotic irrigation system powered by solar panels, detailing its design, operating principle, and key advantages compared to existing analogues. A calculation of the proposed solution's economic efficiency is performed, including an assessment of reduced costs for grid electricity and fuel resulting from the elimination of diesel generators. The obtained results confirm the feasibility of implementing multifunctional, solar-powered robotic systems within the context of modern agriculture.

Models and Technologies for Applying Neuro-Symbolic Intelligence to Multifactor Forecasting of Feed Wheat Yield

Unknown — 2026-09-24

The paper examines ways to improve the quality of multifactor forecasts of feed wheat yield through the combined use of statistical initial data as well as fuzzy-possibilistic and neural network approaches and models. The problem of multifactor forecasting of temporal changes in feed wheat yield is solved by constructing a multifactor model that describes the dependence of yield on forecasted values of parameters characterizing the state of natural and climatic factors as well as on the expected agrotechnological measures. The use of expert knowledge made it possible to perform preliminary processing of the initial data by removing from consideration factors with weak influence and factors that are costly to monitor, which increased the quality of the yield forecast in the example presented in the article by approximately two times. One-dimensional convolutional neural network models, recurrent neural network models, and a hybrid neural network model based on the sequential connection of blocks of three main types of neural network layers (convolutional, recurrent, and fully connected) were also developed, studied, and tested. The conducted comparative analysis showed that the proposed hybrid model ARIMA + hybrid neural network has a significant advantage in terms of error value and coefficient of determination compared with the other models under study. Approaches to constructing a hybrid architecture that combines fuzzy-possibilistic modeling and neural network methods based on principles close to ontology-oriented neuro-symbolic intelligence are also considered.

Development and Experimental Validation of a Cyber-Physical System for Adaptive Control in Pond Aquaculture

Roman Yurievich Borzin — 2026-09-24

This paper presents the development and experimental validation of a cyber-physical control system designed for pond aquaculture operating in open and dynamically changing environmental conditions. The study aims to enhance aquaculture control efficiency through automated monitoring and adaptive control of key water quality parameters. An analysis of the primary causes of high fish mortality in pond farms is conducted, highlighting the limitations of traditional manual monitoring approaches. A model of a cyber-physical system is proposed, integrating physical, cyber, and control subsystems with the external environment, accompanied by a formal mathematical description of their interactions. Key controlled parameters – water temperature, pH, and dissolved oxygen concentration –are defined, and a correlation analysis is performed on monitoring data. An intelligent monitoring data analysis method, based on multi-criteria decision-making and adaptive control, is implemented using IoT sensor data. A working prototype of the system was deployed and tested at operational pond farms in the Volgograd region. Experimental results demonstrate a significant reduction in monitoring time (up to 95%), an 86% decrease in the frequency of abnormal conditions, and a 9% reduction in feed consumption compared to conventional management methods. The findings confirm the effectiveness, reliability, and practical applicability of the proposed cyber-physical approach for improving the sustainability and productivity of pond aquaculture systems.

The Effect of Enzymatic Hydrolysis of Fish Waste on the Degree of Oil Extraction and its Composition

Angelika Valeryevna anzhelika — 2026-09-24

The aim is to investigate the effect of enzymatic hydrolysis modes of fish waste on the degree of oil extraction from it, the composition of its fatty acids, which are important for the microbial synthesis of biotechnology products. The raw materials used were waste from fish processing plants in the Kaliningrad region: hot-smoked sprat heads, mackerel heads and pike-perch internal organs with an oil content of 12.8-22.4%. Hydrolysis of the raw materials was carried out using the enzyme preparation Alcalase at varying temperature (50–70 ºС), duration (20–60 min.), enzyme dosage (0.025–0.6%). In the experiments, the degree of oil extraction was (% of oil content in raw materials): 60,8–73,6 for sprat; 34,4–53,1 for mackerel; 57,6 - 80,4 for pike-perch. At minimum values of hydrolysis parameters, the lowest oil yield was noted for all types of raw materials. The maximum parameters had different effects on the oil extraction level. No significant differences in the fatty acid composition of the oils obtained using different hydrolysis modes were found. The total content of polyunsaturated fatty acids in all oils samples was high: 25.0–27.1% in sprat; 24.4–27.0% in mackerel; in pike-perch. The maximum content of omega-3 PUFA was found in sprat oil (22.9–23.9%), and long-chain fatty acids in mackerel oil (40.7–48.5%). Taking into account the degree of oil extraction and its fatty acid composition, the following are recommended as rational parameters for fish waste enzymolysis with Alcalase: temperature 50 °C, duration 60 minutes, enzyme dosage 0.3%. Analysis of the composition of fatty acids and published data allowed us to consider the extracted oils as a favorable component for use in the composition of substrates in the microbial synthesis of biotechnology products.

Пути развития рыбохозяйственного комплекса России на региональном уровне

sviridovalena85 — 2026-09-24

The paper examines the current state of the Russian fisheries complex in dynamics over the past ten years, development prospects in the face of foreign policy pressure, sanctions, changes in the domestic economy and its digitalization. The key indicators of the industry for 2014-2024 are analyzed: the volume of fish and seafood catch, the dynamics of aquaculture, export supplies and domestic consumption, and their dynamics. The factors influencing the studied indicators have been identified, including the regional heterogeneity of the industry, a partially outdated fleet, difficulties in logistics and warehousing, and sanctions pressure. The Astrakhan region is considered separately, where there is an industry decline, there is potential for the development of aquaculture and processing of local fish. In this regard, strategies for its development and increasing sustainability are proposed, which relate to focusing on current demand, modernizing production, expanding the range of semi-finished products, and optimizing logistics processes. The final part of the paper presents a multi-criteria KPI system for evaluating the effectiveness of a single industry digital platform. The assessment methodology contains five groups of indicators, an algorithm for calculating the integral indicator, and a scale for evaluating the effectiveness of the platform.

Artificial Intelligence Applications for Automating Fish Age

Tatyana Valentinovna Snytnikova — 2026-09-24

Ensuring access to high-quality, protein-rich foods like fish is vital for human nutrition, making the development of fisheries and aquaculture a global priority. Fishing faces sustainability challenges due to declining aquatic resources, while aquaculture offers scalable solutions but requires optimized growth processes. Accurate fish age assessment is crucial for both sectors: in aquaculture, it informs feeding strategies, breeding selection, and harvest planning, while in fisheries, it supports sustainable quota setting by protecting juvenile populations. Traditional methods for assessing fish age - such as analyzing scales, otoliths, or fin rays - rely on counting annual growth rings, but these methods are labor-intensive and prone to human error. Digital technologies, particularly artificial intelligence and computer vision, are transforming this process. Researchers have demonstrated that neural networks can analyze otolith and scale images with over 90% accuracy, significantly outperforming manual methods. Several software programs have been developed to address this task, but many are complex to use, limiting their accessibility. To solve this problem, Kaliningrad State Technical University has developed user-friendly software that uses a hybrid convolutional-regression neural network to automate age assessment from otolith images. The model achieved 92% accuracy on a test dataset, making it a practical alternative to manual counting. Future plans include adapting the tool for local fish species, creating a mobile app for field use, and integrating it with catch reporting systems. This innovation enhances the efficiency of fisheries and aquaculture.

Physico-Mathematical Model of an Ultrasonic Flow-Through System Based on Fuzzy Logic for Automated Counting of Shrimp Eggs in Aquaculture

whiteeva@list.ru Vladimirovich belyakov — 2026-09-24

This review article presents a theoretical foundation for the development of an ultrasonic flow-through system based on piezoelectric transducers and fuzzy logic algorithms for automated counting of giant river prawn (Macrobrachium rosenbergii) eggs in aquaculture. The study addresses the critical need for non-invasive, high-accuracy monitoring of reproductive processes under conditions of reduced water transparency, where traditional optical and mechanical methods exhibit significant limitations. A comprehensive physico-mathematical model is proposed, integrating fundamental principles of acoustics, wave scattering theory, and impedance matching to describe the amplitude of ultrasonic signals reflected from individual eggs. The model incorporates geometric diffraction coefficients, Fresnel reflection at media interfaces, and exponential attenuation according to the Bouguer–Lambert law. Key design parameters of high-frequency piezoelectric transducers (5–15 MHz) are analysed, including resonant frequency calculation and impedance matching strategies to minimise energy losses. A fuzzy logic controller architecture is introduced, utilising normalised signal amplitude and pulse duration as input variables to classify detected objects while accounting for biological variability and environmental noise. Theoretical projections suggest a ~40% reduction in false alarm rates compared to conventional threshold-based methods. Technical challenges, including temperature-induced sound speed drift and interference from air bubbles, are discussed alongside proposed mitigation strategies involving dynamic frequency correction and power spectral density analysis. The article concludes with a roadmap for experimental validation, algorithm optimisation, and system scaling, positioning the proposed approach as a promising solution for enhancing productivity and sustainability in shrimp aquaculture.

Regression analysis and machine learning models for finding optimal growth parameters of Сherax quadricarinatus in closed water supply installations

Alexander Sergeevich Martyanov — 2026-09-24

The article examines the dependence of the growth value for a promising aquaculture object - Australian Redclaw crayfish (Cherax quadricarinatus) – depending on a number of growing parameters in the installation of a closed water supply system recirculating aquaculture system. To analyze this dependence, the authors use methods of linear regression analysis, as well as approaches related to the creation of machine learning models based on bagging algorithms and random forest. Based on the results of the analysis, a conclusion was made regarding the best models. Thus, simple linear models were not accurate enough to build an effective predictive model, while ensemble models based on decision trees demonstrated a significantly higher degree of accuracy in constructing a regression relationship. At the same time, of the two studied algorithms of ensemble models, taking into account the sample size, the algorithm based on bagging turned out to be relatively more accurate than the algorithm based on a random forest. At the same time, both approaches are considered promising for solving aquaculture problems associated with predicting the efficiency of crayfish farming depending on the cultivation conditions.

Deep Learning–Based Sturgeon Counting and Length Estimation Using Segmentation and Skeletonization

glebtev96 — 2026-09-24

The article discusses the problem of contactless monitoring of sturgeon in aquaculture based on video data. The relevance of the work is related to the fact that digitalization of aquaculture is becoming one of the key areas of the industry's development: farms need to promptly and regularly obtain objective indicators on the condition and size composition of fish without laborious manual procedures. In many practical scenarios, selective trapping, measuring and weighing are still used, which increases time costs and can negatively affect fish. Therefore, solutions are needed to automatically obtain quantitative characteristics from video. An end-to-end method is proposed that combines neural network detection and instance segmentation of sturgeons with subsequent calculation of biometric metrics. According to the predicted masks, the frame is resized and morphological cleaning is performed, then the central line (skeleton) of the object and its length in pixels are calculated. . The result of the algorithm is the indicators for the frame of the video stream: the number of fish detected, the lengths of individual individuals, as well as the average, minimum and maximum lengths. Examples of the method's operation in real-world shooting conditions and the results of training the segmentation model are given

The influence of hydrobionts on net construction

karina — 2026-09-24

Abstract The study investigates the influence of hydrodynamic backwater on trawl cod-end performance. Conventional biomass‑assessment models fall short in open‑water fisheries, leading to the adoption of hydrodynamic backwater as a critical variable affecting catch‑efficiency. A numerical framework grounded in Navier–Stokes equations and the vorticity‑stream function (ω–ψ) formulation is constructed to simulate cod-end flows under varying design parameters—including inlet diameter, mesh spacing, mesh orientation, and trawling speed. Experimental simulations identify optimal geometries that minimize hydrodynamic backwater and maximize catch‑efficiency. Findings reveal that a reduced inlet diameter and mesh spacing combined with a T90 mesh orientation cut hydrodynamic backwater by 15–20 %. Hydrodynamic backwater escalates sharply at higher trawling speeds, diminishing efficiency; the optimal speed window is 1.5–2.5 m/s. The ω–ψ solutions closely match hydro‑channel experimental data, validating the model’s accuracy. These results emphasize the necessity of incorporating hydrodynamic backwater considerations into net design and provide concrete recommendations for structural optimization to improve trawl performance. Future work should explore adaptive mesh configurations that respond to real‑time hydrodynamic conditions, integrating machine‑learning algorithms to predict optimal mesh spacing and orientation, thereby further reducing hydrodynamic backwater and enhancing selectivity while maintaining high catch rates across diverse pelagic species.

A Computer Vision Pipeline for Real-Time Fish Population Monitoring in Aquaculture: From Dataset Curation to Deployment with YOLOv5s

Aleksandr Stukalin — 2026-09-24

Automated fish counting in Recirculating Aquaculture Systems (RAS) is essential for improving efficiency but remains difficult due to challenging visual conditions and the high cost of commercial solutions. This study presents a cost-effective computer vision pipeline developed through an iterative, data-centric methodology to overcome these barriers. An initial pilot dataset, captured in a production RAS, diagnosed pervasive issues such as water glare and low contrast. These findings informed the design of a targeted preprocessing stage using Contrast Limited Adaptive Histogram Equalization (CLAHE) and directed subsequent acquisition of an enhanced second dataset with optimized hardware. To build a robust detection model, a two-stage training strategy was employed. A YOLOv5s model was first trained on the initial challenging data, and then fine-tuned on the enhanced, preprocessed dataset. A custom lightweight tracking algorithm was developed to maintain individual fish identities for accurate counting in dense populations. The complete system was integrated into a desktop application for practical deployment. Validation on independent operational videos demonstrated a high efficiency in real-world conditions. This work delivers an affordable alternative to expensive commercial monitoring systems, providing a scalable and practical tool for data-driven management that is particularly accessible to small and medium-sized aquaculture enterprises.

Efficient Neural Network Model Training for Fish Species Classification Using Attention-Enhanced MobileNetV3 in Aquaculture Applications

Nghia Le Van — 2026-09-24

Accurate fish species classification is a critical requirement in intelligent aquaculture management, yet existing deep learning models struggle to simultaneously achieve high accuracy and computational efficiency under resource-constrained conditions. This paper proposes a lightweight attention-integrated framework combining MobileNetV3 with the Convolutional Block Attention Module (CBAM). Two variants are developed: MobileNetV3-Large+CBAM achieves 98.98% accuracy, 98.90% F1-score, and 99.66% Top-3 Accuracy at 17.64 MB, while MobileNetV3-Small+CBAM offers an ultra-lightweight alternative with 98.01% accuracy at 6.50 MB and 1.59 GFLOPs. Both CBAM-augmented variants consistently outperform their baselines while introducing less than 3% additional FLOPs and model size. Experiments on a 31-species dataset of 13,304 images confirm the effectiveness and practical viability of the proposed framework for intelligent aquaculture monitoring, with broad applicability across automated surveillance, quality control, biological research, and education.

Computer Vision as a Measurement Channel in an AIoT Cyber-Physical Pond Aquaculture System: A System Analysis Approach

sparky — 2026-09-24

Pond aquaculture is constrained by labor costs, environmental variability, and the need for stable water quality under uncertainty. IoT sensor networks provide continuous measurements of key water parameters, but they remain “blind” to fish behavior and stock conditions that affect feeding efficiency and early warning of adverse events. This paper extends a cyber-physical pond aquaculture system by introducing computer vision (CV) as a dedicated measurement channel within a closed-loop AIoT (AI + IoT) architecture. From a systems analysis perspective, we formalize the system boundaries, functional modules, data flows, and quality-of-service/quality-of-data constraints for real-time operation. A unified observation model is proposed that synchronizes sensor telemetry and video-derived metrics (fish count, activity level, spatial distribution) via timestamp alignment and confidence-aware data fusion. The fused state estimate drives a hierarchical control logic integrating adaptive regulation of aeration/feeding with safety rules and fallback modes under degraded sensing. A scenario-based evaluation framework is described, including environmental disturbances, sensor faults, video occlusion, and network delays. Illustrative results demonstrate that the vision-enhanced system reduces time spent in unsafe low-oxygen conditions and improves overall water quality indices compared to a sensor-only baseline, while meeting real-time constraints. The approach provides a high-level blueprint for designing and validating AIoT-enhanced aquaculture systems using computer vision as a new measurement modality.

Multiphysical similarity of behavioral characteristics of hydrobiont in the World Ocean

pavel_nasenkov — 2026-09-24

This article discusses a modern approach to studying aquatic organism be-havior, combining hydroacoustic methods, machine vision, and physical modeling. Currently, echo recordings are being decoded using AI to estimate biomass and allowable catch. The widespread use of hydroacoustic methods (HAM) for quantitative population census is discussed; however, these methods require high equipment costs. The authors note that direct observations are rare, requiring automation: machine vision, augmented reality, and mathematical modeling to collect statistics and understand growth dynamics. The article identifies five groups of studies: registration methods, physiology, social behavior, chemical factors, and engineering solutions. The importance of multiphysics modeling and numerical experiments is emphasized, which allow for the prediction of optimal trawl performance and resource manage-ment without expensive field observations. A review of the physical similarity criterion based on dimensional theory and the need to maintain the scale of geometry, mechanics, hydrodynamics, and light properties is provided. The authors propose a transition from integrated statistics to a full distribution analysis, which will lead to increased forecast accuracy and provide a more complete picture of population structure. Overall, the article emphasizes the integration of modern technologies and scientific approaches for sustainable fish farming management.

Digital integration of economic systems of the full cycle of the agro-industrial complex while ensuring food security

Maria Yuryevna Karelina — 2026-09-24

This article examines a fundamental contradiction in the digitalization of the agribusiness sector: the need for end-to-end government oversight to ensure food security and the desire of agricultural producers to maintain sovereignty over their data. The authors advocate for a shift away from centralized data collection models in favor of a decentralized digital ecosystem built on the principles of federated data management (Data Mesh). The key element of the architecture is the "agri-node" – an autonomous edge computing cluster that provides local processing, filtering, and validation of primary data and transmits only trusted derived aggregate metrics and events to the external environment. The three-tier processing topology ensures efficient distribution of computational loads, the use of differential privacy mechanisms for inter-farmer analysis, and the combination of operational management at the local level with strategic planning at the national level. The proposed platform creates the conditions for creating a complete digital product footprint – from field to store shelf - increases the effectiveness of support through targeting and evidence-based support, and lays the technological foundation for implementing a food security strategy.

Digital Technologies as a Driver for the Green Transformation of the Agro-Industrial Complex: A Systemic-Institutional Approach

golovko178 — 2026-09-24

This paper investigates the role of digital technologies as a driver for the green transformation of the agro-industrial complex (AIC) from a systemic-institutional perspective. The authors argue that technological solutions – such as precision farming systems, big data platforms, and blockchain – serve not only as tools for enhancing efficiency but also as a key factor in overcoming the institutional barriers to this transition. Drawing on theories of path dependence, institutional logics, and transaction costs, the study analyzes how digitalization can reduce the costs of adopting sustainable practices and harmonize the interplay of state, market, and community logics.

Based on empirical data and comparative case studies, the paper presents a multi-level model of the impact of digital technologies on the macro-, meso-, and micro-levels of the AIC. It reveals the dual nature of digitalization in Russia, where the active adoption of basic ICTs coexists with a "lock-in" in mastering integrated, "cross-cutting" technologies. The conclusion emphasizes the need for targeted institutional design that shifts the focus of state support from subsidizing assets to developing digital ecosystems and services tailored for small and medium-sized farms.

Digital transformation of the grain sub-complex of Russia

depressante — 2026-09-24

В статье исследуется цифровая трансформация зернового подкомплекса Российской Федерации как системный процесс, затрагивающий производственные, инфраструктурные и институциональные элементы воспроизводственного цикла зерна. В отличие от исследований, фокусирующихся преимущественно на технологических аспектах цифровизации, работа рассматривает её в увязке с уровнем материально-технической обеспеченности отрасли и параметрами воспроизводства машинно-тракторного парка.

Показано, что структурный дефицит техники и низкие темпы обновления парка выступают объективным ограничителем цифровой трансформации отрасли. Обосновано, что даже при условии оснащения всей новой техники цифровыми решениями достижение системного эффекта требует длительного периода.

Предложена двухконтурная модель ускорения цифровизации, предполагающая одновременную интеграцию цифровых решений на этапе производства техники и модернизацию действующего парка. Показана экономическая целесообразность такого подхода: стоимость интеграции цифровых систем при производстве техники составляет незначительную долю её цены, а эффекты от внедрения систем точного земледелия обеспечивают значительное снижение производственных издержек и рост устойчивости урожайности. Отмечено, что цифровизация может рассматриваться не только как инструмент повышения эффективности производства, но и как фактор структурной трансформации экспортно-ориентированной модели зернового рынка.

An Intelligent Module for Estimating the Investment Attractiveness of Agricultural Lands in a Region

makarovskikh — 2026-09-24

This research presents an intelligent module for estimating the investment attractiveness of agricultural lands, addressing the complex interaction of geospatial and economic factors in Russia. We developed a novel hybrid methodology combining Gower distance-based clustering with SHAP (SHapley Additive exPlanations) feature weighting to generate an interpretable investment index. Applied to a dataset of 335 land objects characterized by eight mixed-type features, our approach automatically determined an optimal two-cluster structure, effectively distinguishing high-potential objects not far from the infrastructure from remote, less attractive objects. Crucially, we derived data-driven feature weights via a surrogate Random Forest model trained on cluster pseudo-labels, overcoming the limitations of traditional linear hedonic models. The resulting system achieved exceptional performance, demonstrating 98.5% classification accuracy and an F1-score of 0.97. Furthermore, the regression component for rental rate adjustment yielded a low Root Mean Square Error (RMSE) of 15.87 rubles. Implemented in Python 3.12, this framework significantly enhances decision-making for land portfolio management, enabling precise, fair market valuation and optimized rental strategies for agricultural investors. Hence, the developed method can significantly simplify the management of large real agricultural objects portfolios, providing a transparent and reasonable pricing strategy.

Assessment of Food Supply Using the Potential of the Digital Environment

auriairina — 2026-09-24

Adequate and sufficient food provision for the population is a fundamental element of the economic, social, and political security of the state, as well as of the stability and development of the real sector of the national economy. Food supply must align with sustainable development goals and be compatible with long-term environmental requirements. This study aims to examine approaches to assessing the level of food supply that could improve the management system of the national economy and the agro-industrial complex by leveraging digital environment capabilities. The information base comprised works by Russian and foreign authors on the research topic. Methods of analysis and synthesis, abstract-logical and economic-statistical approaches were applied, with Microsoft Office software products used as technical tools. The objects of the study are the food supply of the population and the digital environment. The subject of the study encompasses approaches to methods for assessing food provision using the potential of the digital environment. Based on the research, conclusions were drawn regarding the existence of large arrays of unstructured information, which necessitates prioritizing big data processing methods and situational monitoring; the need to expand the toolkit for assessing of food supply, including using artificial intelligence (AI) capabilities in the digital environment to analyze big data, such as fiscal data operators (FDOs), Yandex.WordStat service, and others; and exploring the potential of using Federal State Information Systems (FGIS) data to develop approaches for assessing and planning food production volumes. This characterizes the current state and necessary requirements for digitalization processes when analyzing the parameters of the country's population food supply. Therefore, given the scale and complexity of these processes, close interaction between the state and business, combined with an enhanced role for economic science, should be anticipated for the effective use of modern digital technologies. Using digital environment data will enable the construction of a multi-level system for assessing population food needs, actual consumption, and substantiating food production plans. Today, addressing these challenges is impossible without integrating information resources from the state and corporate sectors, which allows transitioning to a new level of agricultural production development and food supply assessment.

The Impact of Digitalization on the Sustainable Development of the Regional Agri-Food System: A Case Study of the Leningrad Region

goncharov_k_p — 2026-09-24

This article examines the impact of digitalization on the sustainable development of the agri-food system (AFS) in the Leningrad Region. The study's relevance stems from the need to address specific regional challenges, including a high urban population density, food security requirements, and limited resources in intensive agriculture. The research aims to analyze the role of digital technologies in creating competitive advantages for the AFS and identifying pathways for sustainable food supply chain development. The authors adapt global Sustainable Development Goals (SDGs) to the regional context, identify levels of digital transformation, and systematize sustainability indicators. The methodology integrates international frameworks (SAFA), Russian strategic documents, and scientific literature. The authors propose a comprehensive indicator system organized across four key SDG dimensions: economic, social, environmental, and institutional. Findings reveal that most regional agricultural enterprises remain at the initial digitalization stage, with a direct correlation established between digital transformation depth and SDG achievement potential. The article concludes that digitalization represents not merely an optimization instrument but an essential, comprehensive element of sustainable development strategy, necessitating balanced consideration of economic, social, and environmental aspects in AFS operations.

Features of digitalization of farms in the Leningrad region

evgenia — 2026-09-24

Farms in the Leningrad Region play a significant role in providing food to the local population and surrounding areas, including St. Petersburg. The widespread adoption of digital technologies opens up new opportunities to improve the efficiency and competitiveness of these farms. This includes optimizing production processes, reducing costs, improving product quality, and increasing supply chain transparency. The purpose of this study is to identify and analyze the key features and challenges of digitalization on farms in the Leningrad Region. We used monographic and graphical methods, a survey of farm heads, analysis and synthesis, and a systems approach. The study revealed the low level of digital technology development on farms and identified the underlying causes. The undeniable advantages of new technologies and the importance of maintaining competitiveness necessitate finding ways to overcome these challenges. Therefore, we propose areas for improving digitalization on farms in the Leningrad Region. These areas can be implemented through a combination of state support measures and the efficient use of these resources by their recipients. The results of the study can be used by government agencies at all levels to develop policies regarding the digital transformation of agriculture.

Digitalization as a factor in the development of agriculture in the Krasnodar urban agglomeration

kalitkosvetlana1975 — 2026-09-24

The article considers the aspects and prospects of digitalization of agriculture in the urban agglomeration using the Krasnodar urban agglomeration as an example. The significance of digitalization in the development of the agro-industrial complex of the Southern Federal District in accordance with the Strategy of Spatial Development of the Russian Federation is noted. The key features ( proximity to the consumer; comprehensive development; pendulum migration; production specifics) , problems ( competition from large agroholdings, land use, logistics, preservation of rural identity) and prospects for the development of agriculture in the urban agglomeration ( development of sustainable agriculture, support for small farms, integration into urban supply systems, creation of comfortable conditions for life and work in rural areas of the agglomeration ) are reflected. The main modern forms, directions and key functions of agriculture in the urban agglomeration are characterized. The specialization of agriculture by districts of the Krasnodar urban agglomeration is presented. The key information technologies used in agriculture, including in the agriculture of the Krasnodar urban agglomeration, are described. The effectiveness of implementing a basic digital package for a medium-sized 1,000-hectare agricultural farm in the Krasnodar metropolitan area is determined. State support and regulatory measures for agricultural producers in the Krasnodar metropolitan area are described. Direct savings from using IT in agriculture in the Krasnodar metropolitan area are calculated.

The need for widespread implementation of information technologies for the sustainable development of the agricultural sector in urban agglomeration conditions is substantiated: accumulated positive experience in the use of digital tools, a functioning system of state support, as well as the confirmed economic and social effectiveness of these innovations.

DIGITAL PLATFORM IN THE CONTEXT OF A MULTIFACTOR MODEL FOR ECOLOGIZED INDUSTRIAL BEEKEEPING

komlackig77 — 2026-09-24

Abstract. The relevance and novelty of the research are determined by the need to transform beekeeping into a high-tech production through the introduction of digital technologies. The results of research by domestic and foreign scientists, as well as official regulatory and advisory documents, served as tools for searching and analyzing current ideas about the level of digitalization of the industry. Using the analytical and generalization methods, the concept of a multi-factor model of environmentally friendly industrial beekeeping was formulated, the key element of which is a unified digital platform. Biological, environmental, technological, and economic factors that make up the model’s structure are determined. A platform architecture is proposed, the key functional modules of which are an apiary monitoring module (IoT); an agroecological mapping module; a digital beekeeper’s journal; a bee health module; a blockchain module; a marketplace and logistics module; and an analytical module (Big Data & AI). The potential economic, environmental, and social effects of the platform implementation are identified and substantiated. The article substantiates the need for synergy among three components: accessible and adapted technologies (simplicity, offline operation), effective cooperation among beekeepers, and a comprehensive government policy in the form of financial and institutional support. The participation of scientific institutions is necessary for validating the platform's algorithms and developing forecasting models adapted to local conditions. The importance of training specialists in digital technologies at universities and through practical training centers is emphasized. Particular attention is paid to the problem of integrating small beekeeping farms, which form the basis of Russian beekeeping, into a single digital platform. The specific challenges of small businesses are analyzed. The main obstacles identified include the lack of accessible infrastructure, insufficient broadband, incomplete internet coverage, limited financial resources, and the low level of digital competence of beekeepers. Taking into account the resource constraints of small businesses, a phased integration path into the platform is proposed. The initial step includes a free basic account with access to a honey plant map and basic analytical advice.

Principles of self-organization of industrial ecosystems as a basis for a digital platform for waste management in the agro-industrial complex: inter-industry technology transfer

polyakov — 2026-09-24

This article examines a conceptual approach to designing a digital waste management platform for the agro-industrial complex (AIC), based on the principles of self-organization of industrial ecosystems and mechanisms for intersectoral technology transfer. The relevance of this study stems from the exhaustion of the growth potential of linear models of environmental management, as well as the need to transition to a circular economy in the agricultural sector. The study revealed that current approaches to AIC waste management are fragmented and do not take into account the emergent properties that arise from the network interactions of heterogeneous economic agents in the industry. The paper demonstrates that industrial ecosystems operating on self-organization principles demonstrate high adaptability and resource efficiency due to the spontaneous emergence of cooperative relationships through the exchange of both direct and by-products. The article proposes a proprietary architecture for a digital platform that, rather than prescriptively managing waste flows, creates an institutional and information environment that stimulates self-organization among participants. Particular attention is paid to mechanisms for the intersectoral transfer of organic waste processing technologies borrowed from related industries. The scientific novelty of this work lies in its synthesis of industrial symbiosis theory, the concept of self-organization of complex systems, and a platform approach to agricultural waste management. The proposed model overcomes intersectoral barriers, transforming waste disposal into a driver of economic growth and technological innovation in the agricultural sector.

Organic berry production

helena — 2026-09-24

Abstract. The purpose of the study is to identify technological features, achievements and problems in the development of berries production. The article analyzes the berries production and its organic products. The development of organic production is shown, characterized by an increase in the number of certified producers. Regular consumption of berries affects human health. Berries are included in the composition of functional, healthy and full nutrition, as well as for the prevention of various diseases. There was a tendency to change the structure of berry production in favour of currants, as well as an increase in the production of berries in protected soil. In the future, the organic market is expected to increase demand for berries, the export of frozen berries, the popularization of organic products in society, the introduction of organic products in various forms of nutrition. Main advantages and disadvantages of organic berry production considered. The main problem of the development of organic products is its high price, which is 2-3 times higher than the price of ordinary products. An important part of organic technology is the use of biologics. The transition to organic production is an integral part of the sustainable development strategy of the agricultural sector. Integration of research, technological innovation and active public policy are key factors in the development of competitive organic berry production in Russia

China's experience and success in the organic market

Наталья Александровна natalianikonova — 2026-09-24

The scale of modern global organic production is combined with the steady dominance of individual states in this area. Therefore, the purpose of the study was to analyze China's practical experience in the organic market as a country with a leading position in it. Based on the systematization of strategic documents, an analysis of the prerequisites for the development of organic agriculture in China has been carried out and programmatic actions of state policy have been identified. Among its areas of focus are measures in the field of environmental innovation in general and individual measures to organize a certification system to tighten product quality requirements. Quantitative changes in the functioning of organic production in China are considered using open statistical data. The assessment of the growth of such key indicators as the area of organic land, the number of producers, the level of consumption per capita, etc. The analysis of the features of the Chinese model of production and demand for organic food is given. The types of established models of land use and the main economic system in the village are shown. The classification of consumers of organic products and the existing problems of their promotion on the market is presented. It is concluded that the necessary institutional conditions have been created in China for the successful development of the organic agriculture sector, taking into account national specifics, historical conditions, as well as effective state policy in the countryside to stimulate the active activity of peasants.

Legal Regulation of Organic Agriculture in the People's Republic of China

Marina Anatolyevna Ermolina — 2026-09-24

This article provides a comparative legal analysis of claims for the establishment of land plot boundaries filed by land users in the Russian Federation and the United States. It identifies a number of problems arising in the consideration of this category of cases by courts of various instances. These problems include the complexity of the subject of proof in boundary disputes, an excessive reliance by judges on the conclusions of cadastral engineers, the underdeveloped conceptual framework for forensic land surveying expertise, its methodologies, as well as requirements for the preparation of expert opinions in land disputes, and the lack of uniform judicial practice in their consideration.

The aim of the research is to identify ways to improve Russian legislation in this area, particularly through the incorporation of legal constructs successfully applied in the United States. The principal research methods employed are comparative legal, formal legal, and systemic methods. General and specific scientific methods (analysis and synthesis) are also applied. An analysis of judicial practice has helped to identify the main features and conflicts in boundary disputes in the two countries. Concepts such as the "actual location of a plot's boundaries" and the "actual location of adjacent plots' boundaries" are examined, which can only be confirmed through the opinion of a qualified forensic expert.

A comparative analysis of the resolution of such disputes in individual US states has allowed for an examination of the specific features of their settlement mechanisms from the perspective of their potential incorporation into domestic legislation. For instance, in the United States, the roles of land surveyors are clearly defined at the legislative level, both in the context of alternative dispute resolution and at the litigation stage. In the Russian Federation, a current problem is the delineation of the forms of participation of a cadastral engineer as an expert (the key feature of engaging a cadastral engineer as an expert is that they conduct a land surveying expertise), a witness, or a specialist, which may lead to the violation of the rights of trial participants.

The research goal has been achieved by identifying mechanisms of legal regulation in the field of land management. The authors have drawn an important conclusion about the necessity of establishing a new type of forensic examination – forensic cadastral expertise – due to the specific nature of land legal relations. The article notes that Russian legislation currently lacks a definition for forensic land surveying expertise, despite the high demand for such examinations. Presently, the procedure for conducting forensic examinations is regulated by legal norms under which real estate objects (the objects of forensic land surveying expertise) cannot be classified as objects of land management. A number of measures are proposed to improve legal regulation in this area, including amendments to legislation on cadastral activities, the adoption of legal acts containing requirements for the qualification of cadastral engineers as experts, empowering the public-law company "Roskadastr" with the authority to promptly resolve land disputes out of court, and other mechanisms aimed at creating legal constructs that facilitate the successful resolution of land boundary disputes. The article also examines the foreign legal doctrine of resolving disputes over the boundaries of adjacent land plots through the tacit consent of their owners, which, in the authors' opinion, could be incorporated into Russian legislation and considered as a basis for establishing the boundaries of land plots on the ground.

Use of a biologically active lake sapropel–based preparation in calf feeding under the conditions of the Novgorod Region

lashkova0410t — 2026-09-24

The aim of the study was to evaluate the effectiveness of using a biologically active sapropel-based preparation in the feeding of farm animals and to assess its effect on the productivity of young stock. The study was conducted on Holstein calves aged four months after weaning at the Ermolin skoye peasant farm in the Novgorod Region. The effects of the preparation on nutrient digestibility, biochemical status of the experimental animals, absolute and average daily weight gain, and feed conversion were evaluated. Based on the principle of analog selection, three groups (n = 10) were formed: one control group and two experimental groups. Calves in the experimental groups received, in addition to the basal diet, 5 and 10 mL of the supplement, respectively. The results showed that supplementation with 5 mL of the preparation increased the digestibility of major dietary nutrients by 1.56–3.73 percentage points and improved the protein index, indicating enhanced protein metabolism, bringing it close to the physiological norm (0.76 g/L). The absolute and average daily weight gains of calves in the first experimental group exceeded those of the control group by 8.8% (P < 0.001). Administration of 5 mL of UDGSS reduced the consumption of digestible protein per 1 kg of live weight gain by 8.2%, energy feed units by 8.1%, and metabolizable energy by 9% compared with the control group. Increasing the supplement dose resulted in higher expenditures of digestible protein and metabolizable energy per unit of weight gain by 14.8% and 14.9%, respectively. Experimental data indicate that the optimal dose of the biologically active UDGSS supplement in the diets of young animals aged four to twelve months is 5 mL per head per day. Increasing the dose to 10 mL is not justified, as it does not enhance the positive effect and instead leads to deterioration of physiological and productive parameters.

Efficiency of BSFL conversion of grain waste into protein meal for animals

Roman Nekrasov — 2026-09-24

The use of grain waste in BSFL cultivation technology represents an innovative approach aimed at increasing sustainability and improving the economic performance of agribusinesses. The aim of the study was to compare the effects of different feed mixture compositions on the chemical composition of BSFL and to assess their nutritional potential for producing protein meal from dried biomass. The experiment was conducted under laboratory conditions, cultivating BSFL on a grain mixture (GM) and grain waste (GW). The final analysis demonstrated that larvae grown on GW are a more efficient option in terms of biochemical value and nutritional potential. They provide maximum protein content and a sufficiently high amino acid ratio, making them a food source for farm animals and a substitute for traditional feed. The obtained results open up prospects for using agricultural waste for the sustainable development of larval cultivation technologies and the creation of environmentally friendly and cost-effective methods for producing high-quality feed.

Black soldier fly (hermetia illucens) as a source of new biologically active substances of protein nature

anton_utkin — 2026-09-24

The black soldier fly (Hermetia illucens) is a promising organism for the bioconversion of organic waste. The symbiotic microflora of the larval gastrointestinal tract plays a key role in this process, which can also serve as a source of biologically active compounds, including antimicrobial peptides (AMP). The purpose of this work was to search for producers of biologically active substances among the saprophytic microbiota of black soldier fly (BSF) frass larvae of H. illucens, as well as to evaluate the antimicrobial activity of protein lyophilizates obtained from insect tissues. The study involved the cultivation of larvae on five different substrates, microbiological analysis of BSF frass flushes, and DNA isolation followed by sequencing of the 16S rRNA gene to identify bacterial isolates. In parallel, protein extracts were obtained from larval biomass by alkaline extraction followed by purification by dialysis and their antimicrobial activity against Escherichia coli and Bacillus subtilis was evaluated.

As a result, the strains Heyndrickxia sporothermodurans and Heyndrickxia oleronia were identified, which, according to phylogenetic analysis, are potential producers of AMP (amylocyclin, fengycin). It was shown that protein fractions with a molecular weight above 20 kDa have lytic activity against test cultures, while fractions less than 20 kDa showed no pronounced effect. The data obtained indicate the prospects of using both the microbiota of frass and the larvae of the black soldier fly to search for new antimicrobial agents that can be used in medicine and the food industry as an alternative to conventional antibiotics and chemical preservatives.

Dispersed state evaluation by dynamic light scattering for alkaline suspension of black lioness fly frass (zoohumus) after its mineralization

jan88 — 2026-09-24

Alkaline suspensions of zoohumus from black soldier fly (Hermetia illucens) were studied before and after its additional mineralization. Four samples of zoohumus differing in processing stage and with pH from 7.6 to 11.7, were analyzed by Zetatrac (Microtrac Inc.) particle size and zeta-potential analyzer using dynamic light scattering (DLS) in the beat light spectroscopy (Doppler) mode. It was shown that all the studied samples were in a state of colloidal instability: the ζ-potential was +3.3…+3.8 mV at high ionic strength (I ≈ 55-65 mM, electric conductivity 5.4-6.2 mS/cm), which led to compression of the double electric layer to κ⁻¹ < 1.4 nm. Samples after mineralization (No. 1 and No. 2) were characterized by tri- and bimodal distribution of intensity with particle size from 100 to 6500 nm (and higher) at PDI of 2.418-2.960; the initial suspensions (No. 3 and No. 4) – by a bimodal distribution with particles size from 150 to 4000 nm at lower PDI (1.794-1.986). Samples 3 and 4 had higher concentration of organic carbon C_org (4.77-5.13 g/L compared to 3.17-3.43 g/L in samples 1 and 2) and exhibited pronounced organoleptic signs of active biochemical degradation. A diagnostic criterion for the completeness of suspension stabilization based on the C_inorg/C_org ratio is proposed: values >0.32 correspond to a mineralized state, while <0.19 correspond to the original suspension. Additional mineralization is shown to reduce the risk of an unpleasant odor and increase the shelf life of the preparation. However, it is associated with a partial loss of humates due to their coagulative precipitation. The obtained results have practical significance for the development of technologies for the preparation of liquid organo-mineral fertilizers based on H. illucens zoohumus.

EFFECT OF GLYPHOSATE ON GUT MICROBIOME BIOMARKERS ASSOCIATED WITH REPRODUCTIVE LONGEVITY IN LAYING HENS

filippova — 2026-09-24

Glyphosate is herbicide that is now widely used in agriculture. Glyphosate has a direct effect not only on plants but also on the gut microbiome of farm animals and poultry. This study examined the effects of glyphosate on the gut microbiome biomarkers of laying hens depending on their reproductive longevity. The results of the study revealed a relationship between glyphosate exposure, the composition of the gut microbiota, and the productive longevity of laying hens. It was found that the herbicide can induce changes in the bacterial community. Glyphosate had the most significant effect on the Firmicutes/Bacteroidota ratio. In the group with high reproductive longevity, glyphosate led to a 6.36% increase in Firmicutes and a 5.78% decrease in Bacteroidota. In the group with low reproductive longevity, it increased Firmicutes by 3.44% and decreased Bacteroidota by 4.05%. These microorganisms can be considered markers reflecting the negative impact of the herbicide on the microbiome. Glyphosate reduced the proportion of groups responsible for fiber fermentation and short-chain fatty acid synthesis, such as Bacteroidetes and Ruminococcaceae. Furthermore, laying hens from a line with high reproductive longevity were found to exhibit significantly greater resistance to the negative impact.

BIOINFORMATICS ANALYSIS OF THE GENOME OF E. FAECALIS E-10 STRAIN ISOLATED FROM COW ENDOMETRIUM

elenayildirim — 2026-09-24

Studying the microbiome of the cow's reproductive system is crucial for maintaining the animals' reproductive capacity. In 2025, the E. faecalis E-10 strain was isolated from the endometrium of a healthy Ayrshire cow kept at the Valaam Monastery eco-farm. The aim of the study was a whole-genome analysis of the strain using the MiSeq sequencer (Illumina, Inc., USA) and bioinformatics tools, including the RAST (https://rast.nmpdr.org), KEGG (https://www.kegg.jp), and Prokka (https://github.com/tseemann/prokka) databases. Whole genome analysis of the E. faecalis E-10 strain showed that the genome consists of 108 contigs and has a total length of 2,882,409 bp. Analysis of the antimicrobial activity of the strain showed that the largest growth inhibition zones (up to 29±1.5 mm) were noted for test cultures of Clostridium perfringens, Streptococcus agalactiae, Aspergillus spp. and Penicillium spp. The genes for the synthesis of organic acids were found in the genome of E. faecalis E-10, such as ldh1 and ldh2, pta1/2 and ackA, pflA/B, and fumC, frdA, and mae. Genes for resistance to oxidative and osmotic stress were also identified. These included genes encoding glutathione biosynthesis, the CoA-disulfide thiol disulfide redox system, the choline and betaine uptake system, and betaine biosynthesis. These results indicate a potential role for E. faecalis E-10 in maintaining a favorable microbial balance in the endometrium.

Эко-эпидемиология паразитарных болезней птицы в Республике Армения: национальный анализ и его значение для устойчивого контроля

Микаел Джоникович Микаелян — 2026-09-24

Poultry farming is an important component of agricultural production and food security in the Republic of Armenia; however, information on poultry parasitic diseases in the country remains fragmented and confined to regional investigations. The present study aimed to synthesize published data on poultry parasitoses in Armenia and evaluate their epidemiological patterns, environmental determinants and diagnostic limitations.

A structured narrative review was conducted using peer-reviewed publications, regional veterinary reports and official statistical data on poultry production. Epidemiological indicators, including prevalence, geographical distribution, seasonal dynamics and diagnostic methodologies, were comparatively analyzed.

The collected evidence indicates that poultry parasitic diseases in Armenia form a stable enzootic complex dominated by protozoan infections. Coccidiosis caused by Eimeria spp. was the most widespread disease and occurred across foothill, mountainous and high-altitude regions, with seasonal peaks in spring and autumn. Helminth infections, particularly Ascaridia galli, were frequent in backyard production systems and contributed to environmental contamination and mixed invasions.

The predominance of smallholder poultry farming, outdoor keeping and climatic conditions supports continuous transmission. Current diagnostics rely mainly on classical microscopic methods, while molecular monitoring and resistance assessment are lacking. The study provides an integrated national overview and highlights the need for standardized surveillance and sustainable control strategies.

Experimental Study on Physical Properties of Co-composting Cow Manure and Walnut Branches and Load Calculation of Compost Turner

sujian36 — 2026-09-24

To address the lack of physical property parameters during cow manure composting and the insufficient design basis for composting equipment, this study investigated the dynamic variation patterns of the physical properties of cow manure under different composting treatments and applied the measured parameters to the load calculation of the compost turner main shaft. [Methods] Three composting treatments were set up: pure cow manure, cow manure + walnut branches, and cow manure + walnut branches + microbial agent. Referring to soil mechanics test methods, the changes in moisture content, hardness, shear strength, cohesion, and the tangent of the internal friction angle during the composting process were measured. The measured strength data were then used to calculate the maximum torque on the compost turner main shaft. [Results] The study showed that the cohesion and the tangent of the internal friction angle of the compost were negatively correlated with moisture content. In the later stage of composting (moisture content 28.4%), the cohesion reached 38.412 kPa, and the tangent of the internal friction angle was 0.2982. Adding walnut branches improved the compost structure, and adding the microbial agent made the compost looser and reduced compaction. Based on the most unfavorable working condition (all mixing rods buried in the compost with one row perpendicular to the ground), the calculated maximum torque on the compost turner main shaft was 7.28 kN·m. [Conclusion] This study provides reliable basic data for the structural design and power selection of compost turners, offering guidance for the optimization of equipment for the resource utilization of livestock and poultry manure.

A pilot study of antifungal and chemosensitizing activities of two microbial metabolites to assess their applicability in organic crop production as potential biologicals controlling some Fusarium fungi

Larisa A. Shcherbakova — 2026-09-24

Chemosensitization of phytopathogenic fungi to synthetic fungicides is a promising technology that could enable disease control using reduced fungicidal dosages while maintaining the requested antifungal effect through combining of fungicides and sensitizers, i. e., compounds that synergistically enhance the efficacy of reduced dosages. Usage of biogenic sensitizers, which are non-toxic or marginally toxic to fungi, aligns with sustainable agriculture principles. Earlier we demonstrated that a microbial metabolite, 6-demethylmevinolin (6-DMM), mildly inhibited the growth of Fusarium fungi and synergistically enhanced the sensitivity of other fungi to a triazole fungicide Folicur^®. Another microbial metabolite, tacrolimus (FK-506), was reported to improve the action of some medical triazols. Given these data, we explored the growth inhibitory effect of FK-506 and 6-DMM towards several strains of Fusarium graminearum and F. culmorum, and evaluate their chemosensitizing activity for these species using a checkerboard assay. FK-506 was found to demonstrate high strain-specific fungitoxicity, and the species-selective chemosensitization, while 6-DMM exhibited moderate fungitoxicity and looked more promising as the sensitizer of both species. Several 6-DMM/Folicur^® combinations were revealed that synergistically enhanced Folicur^® effect, multiplying the fungicidal impact of its low doses. At the most effective synergistic ratios, the efficacy of the combined treatments almost doubled the additive effect.

SWARD FORMATION IN VARIEGATED ALFALFA UPON SEED INOCULATION WITH ROOT-NODULE BACTERIA SINORHIZOBIUM MELILOTI IN KARELIA

agronomka — 2026-09-24

A key development track for fodder and forage production today is to biologize the processes. Accordingly, much attention is being given to varietal-microbial systems, whose performance is in direct correlation with the plant community’s yield and nutritive value and the efficiency of nitrogen fixation from the atmosphere. The range of forage crops in Karelia is rather narrow and a crop drawing much interest is variegated alfalfa, which boasts high yields and productive longevity combined with drought- and frost hardiness. However, as the soils lack native strains of root-nodule bacteria capable of interacting productively with this legume, seeds have to be inoculated prior to sowing. In 2022-2024, the Vilga Agrotechnology Laboratory conducted field studies of sward formation in variegated alfalfa of the following varieties: Pastbishchnaya 88, Taisiya, Agniya VIK, and Lyusya upon inoculation with several strains of root-nodule bacteria S. meliloti (master seed strain 415 (control), А-1, А-5, and SKhM-1-105) to determine the inoculation effects on plant community formation and to select the varietal-microbial systems best suited for the region. The studies have demonstrated that inoculation has a tangible effect on herbage formation and that in southern parts of Karelia variegated alfalfa can form robust communities with an average yield of up to 8.8 t/ha dry weight in pure crops. The highest productivity in Karelia was exhibited by combinations of the Agniya VIK and Lyusya varieties with the А-1 and SKhM-1-105 strains.

Preliminary Characterization of Cultivable Epiphytic Microorganisms Associated with Eryngium caucasicum Trautv

Susanna Stalikovna Mirzabekyan — 2026-09-24

Plant surfaces host diverse microbial communities that form the phyllosphere microbiota and may influence the stability and biological properties of plant raw materials. However, information about cultivable epiphytic microorganisms associated with medicinal and wild edible plants of the South Caucasus region remains limited. The present study aimed to obtain preliminary microbiological characteristics of microorganisms inhabiting the aerial parts of Eryngium caucasicum Trautv.

Leaves of two- and three-year-old plants were gently washed in physiological saline to recover surface-associated microorganisms without tissue disruption. Suspensions were inoculated onto nutrient agar and MRS agar and incubated under standard conditions in triplicate.

Cultivation revealed a stable and reproducible community of microorganisms represented by several colony morphotypes, including coccoid, bacillary and yeast-like forms. Colony number and composition varied depending on plant age and processing conditions. Two-year-old plants demonstrated higher counts of filamentous and bacillary colonies on nutrient agar, whereas three-year-old plants showed relatively greater representation of coccoid forms on MRS medium. Microorganisms remained detectable after washing procedures, indicating persistent surface association rather than incidental contamination.

The obtained results confirm the presence of a cultivable epiphytic microbiota on E. caucasicum and demonstrate its variability under different sampling conditions, providing a basis for further functional and taxonomic characterization.

Evaluation of Statins as Potential Bioagents Suppressing the Development of Insect Pests

dimvor — 2026-09-24

This study assesses the potential of a novel plant protection strategy based on limiting the supply of essential sterols to insect pests. The approach involves treating plants with statins that inhibit sterol precursor biosynthesis. Laboratory experiments were conducted using the Colorado potato beetle (Leptinotarsa decemlineata Say) and the greenhouse whitefly (Trialeurodes vaporariorum Westw.) as model organisms. Increasing compactin concentrations significantly reduced the average weight of L. decemlineata larvae (by 40.6% at 0.1%), pupae (by 15.2% and 22.8% at 0.05% and 0.1%, respectively), and adults (by 14.9% and 22.9% at 0.05% and 0.1%, respectively). Compactin at 0.05% and 0.1% also prolonged the larval stage by 4.0 and 4.8 days, respectively. In contrast, 0.1% lovastatin had no significant effect on the beetle development. For the greenhouse whitefly, the results were inconclusive regarding the feasibility of compactin for developmental suppression. These discrepancies may be attributed to differences in the systemic transport of compactin and lovastatin within plants, differential sensitivity of HMG-CoA reductase to specific statins, or species-specific physiological traits. Overall, HMG-CoA reductase inhibitors show promise for insect pest management, although further studies are required.

THE ROLE OF STRAW AND BIOLOGICAL PRODUCTS IN INCREASING BIOLOGICAL ACTIVITY IN SOILS AND THE PRODUCTIVITY OF AGRICULTURAL CROPS USING THE EXAMPLE OF SPRING WHEAT

licosyl-1licosyl — 2026-09-24

Wheat accounts for 27% of all grain crops produced globally. Increasing its yield depends on the use of biological preparations. Research conducted in the steppe zone of the Altai Territory to study the effect of GSN series preparations based on organic compounds, macro- and microelements, and a complex of microorganisms used in the technology of growing spring wheat using the no-till system on the soil, for seed inoculation and as top dressing during plant vegetation, made it possible to establish a positive effect on the agrochemical properties of the soil. By the end of the wheat growing season, they increased the development of saprophytic microorganisms by 1.8-4.1 times, amylolytic bacteria by 1.9-3.1 times, while the number of fungi decreased by 1.3-1.9 times. The organic matter transformation coefficient (PM) increased by 1.8-4.4 times and was in an average correlation with the humus content (r = 0.44). Applying them only to soil and seeds increased catalase activity by 1.02-1.35 times, while additional crop treatment increased it by 1.54-1.94 times. Peroxidase activity changed less significantly than polyphenol oxidase activity, and the humus formation coefficient in the treated variants was greater than or equal to 1.0. It had a close correlation with humus content (r = 0.89). The use of GSN series preparations increased spring wheat yield by 0.25-0.97 t/ha compared to 3.41 t/ha in the control. Moreover, protein content increased from 10.52% in the control by 0.66-1.49%. More significant changes in both the soil and plants were noted with consistent and repeated use of the GSN series complex of preparations.

EFFECT OF ARKSOIL NITROGEN AND ARKSOIL PHOSPHORUS BIOFERTILIZERS ON THE PRODUCTIVITY AND NUTRITIONAL VALUE OF WINTER RYE GRAIN IN THE NOVGOROD REGION

zevs1954 — 2026-09-24

The research was conducted in the Novgorod region in 2023-2025 on a sod-podzolic medium-cultivated soil in an experimental field at the Novgorod Research Institute of Agriculture, a branch of the St. Petersburg Federal Research Center of the Russian Academy of Sciences, on two backgrounds of mineral fertilizers (background 1 without fertilizers, background 2 based on the planned yield of winter rye grain). The object of the study was the Volkhova variety of winter rye and the biofertilizers Arksoil Nitrogen and Arksoil Phosphorus. The research demonstrated the high efficiency of the used microbial fertilizers. In the average of three years of research, in variant 8, on background 2, the best average annual grain productivity of 7.7 thousand tons of feed units per hectare was obtained when Arksoil Nitrogen and Arksoil Phosphorus were included in the technological operations twice. In this variant, the average annual nutritional value of grain fodder was 0.41 tons of digestible protein for cattle, with a content of 53.3 g per 1 feed unit, 63.0 GJ of exchange energy for cattle, and more than 5.7 tons of dry matter, with a low energy consumption of 2.7 GJ/ton and a high energy efficiency coefficient of 6.2.

Results of Potato Hybridization Research in Mongolia

nyamgerel_81 — 2026-09-24

Potato crossing success depends on several external factors including weather conditions, growing practices, and maintenance. To increase crossing success, breeders should have prior knowledge of the flowering intensity and duration of varieties, as well as the pollen fertility of male parents. Our experimental results demonstrated that both open-field weather and greenhouse conditions significantly influenced potato hybridization outcomes. When air humidity fell below 60 percent and temperatures exceeded +35°C, breeding success dropped below 10 percent. In 2015, the number of emasculated flowers and combinations reached their lowest values compared to other years, with flower buds drying out and dropping due to hot weather conditions.

To develop superior potato varieties adapted to Mongolian agro-ecological conditions, the hybridization method has been employed in the potato breeding program since 2014. During this period, we performed 223 cross combinations and emasculated 7,780 flowers. According to our hybridization results, 1,953 flowers set berries, achieving a crossing success rate of 24.1 percent. The year 2014 was particularly successful, with a crossing rate of 47.8 percent, while 2019 showed the lowest rate at 5.8 percent. In 2018, we emasculated 2,299 flowers and harvested 742 berries—the highest numbers recorded.

Climate effects on Barley yield in Mongolia

javzandulam80 — 2026-09-24

This study examined the influence of climatic factors — principally seasonal precipitation and temperature sums — on summer barley (Hordeum vulgare L.) yield formation at the Plant Science Agricultural Research Institute, Darkhan-Uul Province, Mongolia, over the period 2003–2015. A total of 145 varieties and breeding lines were evaluated under rainfed conditions. Study years were classified by the Hydrothermal Coefficient (HTC) of Selyaninov into humid, normal, dry, and drought categories. Yield ranged from 1.1 to 41.4 t/ha with an overall mean of 19.2 t/ha. The correlation between growing-season precipitation and yield was r = 0.68 across all years, rising to r = 0.91** in drought years. Compared with normal years, yields were 7.4% higher in humid years but declined 43.6% in dry years and 82.2% in drought years. Key yield-structure components — productive stem count (r = 0.82), plant height (r = 0.82), and total stem number (r = 0.75) — showed the strongest correlations with yield at the 99% confidence level. Grain protein content was positively correlated with June–August temperature sums (r = 0.57–0.62*), while grain starch showed an inverse relationship with late-season temperature. These findings highlight the overriding role of water availability on barley productivity in Mongolia's continental climate and underscore the need for drought-tolerant varieties in national breeding programs.

The wheat breeding in Mongolia

Bayarsukh Noov — 2026-09-24

The main feature of Mongolia’s climate is extreme continental nature. According to the soil, climate condition and farming system Mongolia is divided into 5 distinct crop production zones. The short growing season, low precipitation and high evaporation are the over-riding constraints in Mongolian agriculture. Particularly, unseasonable frosts and severe drought can cause harvest losses of 10 to 30 % of crops. Spring wheat is the dominant staple food crop, which is cultivated on about 90% of agricultural land in Mongolia. Systematic crop breeding started in the 1960s in Mongolia and cereal crop breeding have been developed through 5 steps. Wheat breeding objective mainly focused on the improvement of high grain yield, early maturity, drought tolerance, disease resistance, high quality and nutritional value, irrigation and duruim wheat. During 60 years of study over 110 cereals crop varieties have been developed. The recently released and commercialized new spring varieties Darkhan 144, Darkhan 131, Darkhan 160, Darkhan 193, Darkhan 212, Darkhan 172 have got average grain yield 2.0-3.5 t/ha and comprises about 40% of total sowing area in the county over past years. In the future, the major target of spring wheat breeding programs in Mongolia will focus on the crop yield potential, quality and, in particular, the improvement of drought and heat tolerance which have obvious negative effects to crop potential in recent years.

Technological and design solutions for combined microwave-ultrasonic inulin extraction

Yuri Maksimenko — 2026-09-24

The article discusses a promising method for extracting inulin from plant raw materials. The aim of the work is to develop and scientifically substantiate the method, operating parameters and design solutions for microwave-ultrasonic extraction of inulin from various raw materials. Traditional methods of inulin production are characterized by high energy intensity, duration and risk of thermal degradation of the target product. A scheme is proposed that combines microwave exposure (frequency 2450 MHz) and ultrasonic exposure (frequency 22 kHz, intensity 50 W/cm2) to the extraction mixture in a single recirculation circuit. Microwave exposure provides rapid volumetric heating of intracellular moisture and loosening of plant tissues, while ultrasonic cavitation intensifies the destruction of cellular structures and, as a result, mass transfer processes. A machine and hardware scheme of the method has been developed, including the stages of raw material preparation, combined extraction, filtration, clarification, concentration and drying. The optimal process parameters have been experimentally substantiated: a 1:4-1:8 hydraulic module, a temperature of 338-348 K, a cycle duration of 20-40 minutes, and a circulation rate of 20-30 volumes/hour. The combined method reduced the extraction time by 1.5 times compared to known methods while maintaining a high inulin yield (up to 95-98%). The finished product meets the requirements of the regulatory documentation for physico-chemical (humidity 4-6%, inulin content ≥ 95%, ash content < 0.2%) and microbiological parameters. The proposed method ensures the preservation of the molecular weight and prebiotic activity of inulin. The proposed solutions are scalable, patent-protected, and adaptable for processing various types of inulin-containing raw materials.

Water Pricing and Irrigation Economics: An Overall Assessment of Policy, Practice, and Sustainability in Agriculture

pratyushkumarirath — 2026-09-24

Water plays a crucial role in agricultural productivity, yet its inefficient allocation and underpricing remain major challenges for sustainable irrigation management. This paper examines the economic and policy dimensions of irrigation water pricing, with particular focus on its implications for resource efficiency, financial sustainability, and ecological balance in agriculture. Agriculture accounts for nearly 80% of total freshwater withdrawals in India, while irrigation tariffs remain significantly lower than the actual cost of water delivery, resulting in inefficient use and increasing pressure on water resources.

The study reviews various irrigation water pricing mechanisms including area-based charges, volumetric pricing, block tariffs, and water markets, highlighting their advantages, limitations, and applicability in developing country contexts. It also analyzes the gap between the cost of irrigation infrastructure and the tariffs charged to farmers, emphasizing the role of subsidies and political economy constraints in shaping current pricing policies.

The findings suggest that ineffective pricing structures, weak cost recovery, and institutional limitations contribute to unsustainable water use and declining groundwater levels. The paper argues for gradual reforms in water pricing supported by improved measurement systems, strengthened water user associations, and better alignment of agricultural policies. Such reforms can promote efficient water allocation, enhance irrigation sustainability, and contribute to achieving long-term agricultural and environmental goals.

The nitrogen cycle processes as an indicator of oil pollution in agricultural soils

recchi — 2026-09-24

Потребление нефти и нефтепродуктов, а также выбросы их отходов в окружающую среду происходят повсюду, затрагивая также сельскохозяйственные земли. Продуктивность сельскохозяйственных земель зависит от интенсивности питания азотом. Высокотоксичные загрязнители почвы, такие как нефть и нефтепродукты, вызывают значительные изменения интенсивности и направления биогеохимических процессов, которые также влияют на основные процессы азотного цикла. В загрязнённых почвах общее содержание азота меняется, соотношение углерод/азот увеличивается, а содержание лабильных форм азота уменьшается. Загрязненные почвы имеют дисбаланс: избыток углерода и дефицит азота и фосфора. Снижение биодоступного азота приводит к изменениям в функционировании почвенных микробных сообществ. Азот является критически важным компонентом микробного метаболизма и обычно выступает ограничивающим фактором в деградации нефти, несмотря на то, что численность микроорганизмов, способных метаболизировать углеводороды, может увеличиваться. При очистке почв, загрязнённых нефтью и нефтепродуктами, общее содержание азота в почве повышается, что приводит к снижению соотношения углерода к азоту. Оценка реакции процессов азотного цикла на загрязнение почвы нефтью предоставляет возможность оценить экологическое состояние почвы и эффективность рекультивационных работ.

Microbial respiration as an indicator of the efficiency of biopreparations for oil-contaminated soil purification

recchi — 2026-09-24

This paper presents a comparative study of the efficiency of various oil-degrading preparations used to clean natural soil from old oil contamination, using the integrated indicator of microbial respiration rate. The object of the study was the natural sandy loam soil with an oil pollution lasting about 60 years. A comparative study of the effectiveness of five different biological oil-degrading preparations for cleaning soil from petroleum products was conducted in a laboratory experiment under extreme conditions - low air temperature (14-16°C) and without the addition of fertilizers and lime. The initial petroleum products content in the soil was 3400 mg *kg^-1. The indicators of the effectiveness of the biopreparations used in the experiment were the microbial respiration rate, which was determined by the intensity of the soil CO₂ production using the adsorption method, as well as the content of petroleum products in the soil, which was determined using IR spectrometry. Over a 28-day experiment, depending on the preparation type, 8-16% of the petroleum products were mineralized from their original content. Two biopreparations, “Destroyl” and “Nord”, did not affect the activity of biodegradation, the other studied preparations, “Devoroil”, “Soyleks” and “Aborigen”, intensified the process of petroleum products’ degradation by 1.5, 1.8 and 2.0 times, respectively. The reason for such significant differences in the effectiveness of the studied oil-degrading biopreparations was their specific composition. Microbial respiration has been proven to be a highly informative indicator of the activity of the petroleum hydrocarbons’ mineralization in soil. A strong correlation was established between the rate of microbial respiration and the dynamics of petroleum products in the soil (R > 0.80).

EXPERIMENTAL STUDY OF THE EFFICIENCY OF A ROBOTIC SYSTEM FOR PRECISE FERTILIZER APPLICATION TO INCREASE RESOURCE EFFICIENCY IN CROP PRODUCTION

moskvichev — 2026-09-24

This study presents research on the effectiveness of using the autonomous robotic system "AgroBot-PN" for the spot application of liquid fertilizers during pre-sowing preparation. Improving the efficiency of mineral fertilizer use is a key component of resource-saving agriculture in the context of rising prices for agrochemicals and stricter environmental requirements. The objective of this study was to compare the agrotechnical and economic effectiveness of an autonomous robotic system for precision (pre-sowing) regulation of starter fertilizers under sunflower compared to the conservative broadcast method. In a 2025 field experiment on leached chernozem, a two-factor plan was used: the application method (robotic point and round broadcast) and fertilizer rates (N30P30K30 and N45P45K45). It was found that robotic precision application significantly reduces fertilizer consumption by ~35% while maintaining yield, increasing the fertilizer utilization coefficient by 25–30%, and increasing seed oil content by 1.5–2.0%. An analysis of variance revealed a first-stage reduction in yield (F=87.42; p<0.001). An economic analysis revealed a 33.3% reduction in fertilizer costs and an 18% increase in sunflower cultivation profitability. Practical recommendations for considering robotic systems in row crop separation processes have been developed.