Improving methods for construction of neural networks as a tool for environmentally friendly sunflower protection techniques

Abstract

The object of this study is the pro-cesses of sunflower disease identifica-tion using neural networks and their impact on the efficiency and envi-ronmental sustainability of biologi-cal protection methods. The research addresses the task of improving the diagnosing accuracy of sunflower dis-ease under conditions of limited real-world data. Specifically, this paper focuses on finding ways to enhance neural network design methods in data-scarce environments to improve the environmental sustainability of sunflower protection methods. A key feature of the results is the ability of the synthetic data integration algorithm to achieve high accuracy even with a limited amount of real data, which provides a significant advantage over conventional methods requiring large volumes of information.The application of mathematical modeling and Few-shot learning algo-rithms, combined with Generative Adversarial Networks (GANs) for gen-erating synthetic images, improved diagnostic accuracy to 93–95%, evenwith small datasets. This was achieved due to the model’s high generalization capacity, trained on diverse synthetic data that accounted for varying field conditions.The findings make it possible to effectively apply biological protection methods by optimizing disease diagno-sis based on mathematical modeling of the relationships between environmen-tal conditions and biological agents.The practical significance of the results is the ability for agricultur-al practitioners to employ innovative diagnostic methods to enhance sun-flower yield and reduce dependence on chemical protection agents. The proposed approaches contribute to the implementation of international envi-ronmental standards and could be integrated into agricultural decarbon-ization programs. The implementa-tion of biological protection methods reduces environmental risks, saves resources, and maintains agroecosys-tem productivity.