Interregional Academy of Personnel Management

Yevheniia Znakovska, a researcher at the Interregional Academy of Personnel Management (IAPM), is a co-author of the research paper “AI-Based and Cloud-EDGE Solution for Automatic Wheat States Detection in Smart Agriculture,” published by Springer as part of the Integrated Computer Technologies in Mechanical Engineering – 2025 (ICTM 2025) conference proceedings.

The paper is included in the Lecture Notes in Networks and Systems (LNNS), Volume 1918, a series indexed in Scopus. The study was co-authored by Maxim Ivanytskyi, Yuliya Averyanova, Yevheniia Znakovska, Nadiia Sauliak, and Yevhenii Kirchuk.

The research focuses on the use of artificial intelligence, unmanned aerial vehicles, and cloud and edge computing for automated monitoring of wheat crops. The authors combine digital technologies with practical challenges in modern agriculture, including the early detection of plant diseases.

Artificial Intelligence for Crop Monitoring

The authors examine the use of unmanned aerial vehicles (UAVs) to capture digital images of agricultural crops and subsequently analyse the collected data automatically.

The proposed approach combines UAV technologies, artificial intelligence, cloud computing and edge computing. This architecture enables the collection, transmission and processing of information about crop conditions to support decision-making in precision agriculture.

One of the practical objectives of the research was the automated identification of wheat crop areas affected by wheat leaf rust. To analyse digital images, the authors applied a Convolutional Neural Network (CNN) algorithm.

Integrating UAV, Cloud and Edge Computing

The study demonstrates the potential of integrating several technological components into a single monitoring system. UAVs serve as a tool for collecting visual information about crops, while cloud and edge computing provide the technological infrastructure for processing the collected data.

This approach can be applied not only to disease detection. The information obtained through monitoring can also support the assessment of crop conditions, short- and long-term crop management, and the preparation of datasets required for training machine-learning models.

The combination of UAV, cloud and edge technologies provides a technological basis for the development of digital monitoring systems in precision agriculture, where data can support more informed management decisions.

Neural Network Application and Research Results

As part of the study, the authors tested the use of a CNN model to identify areas affected by wheat leaf rust. The model was trained using digital images of plants.

The experimental results showed an accuracy of approximately 0.8 on the test dataset and 0.7 on the training dataset. The authors note that these results were obtained at an initial stage of the research using a limited number of available images.

The findings demonstrate the potential of machine-learning algorithms for the automated analysis of agricultural crops. Further data collection and model development may contribute to the creation of monitoring systems capable of addressing a broader range of tasks in digital agriculture.

Research and IAPM Sustainable Development Goals

The research contributes to four of IAPM’s Sustainable Development Goals: Goal 2: Zero Hunger, Goal 8: Decent Work and Economic Growth, Goal 9: Industry, Innovation and Infrastructure, and Goal 12: Responsible Consumption and Production.

Goal 2: Zero Hunger is reflected in the use of digital technologies to monitor agricultural crops and support more efficient food production. Automated detection of wheat diseases can provide timely information about crop conditions and support informed agricultural decisions.

Goal 8: Decent Work and Economic Growth is addressed through the technological transformation of the agricultural sector. Automation of monitoring, data processing and machine-learning applications creates opportunities to optimise production processes and develop new technological competencies.

Goal 9: Industry, Innovation and Infrastructure is directly connected to the technological foundation of the research. The study combines artificial intelligence, machine learning, UAVs, cloud computing and edge computing to develop a digital environment for precision agriculture.

Goal 12: Responsible Consumption and Production relates to the efficient use of resources and the improvement of production processes. Digital monitoring provides more detailed information about crop conditions, which can support better-informed planning of agricultural operations.

Overall, the research combines technological innovation with practical challenges in agriculture and demonstrates the interdisciplinary nature of the research conducted by IAPM representatives.

You can access the text of the research paper at the following link:  https://link.springer.com/chapter/10.1007/978-3-032-22372-2_19

Publication Details

Ivanytskyi, M., Averyanova, Y., Znakovska, Y., Sauliak, N., & Kirchuk, Y. (2026). AI-Based and Cloud-EDGE Solution for Automatic Wheat States Detection in Smart Agriculture. In O. Lytvynov, V. Pavlikov, & D. Kritskiy (Eds.), Integrated Computer Technologies in Mechanical Engineering – 2025. ICTM 2025. Lecture Notes in Networks and Systems, 1918, 227–238. Springer, Cham.