Modelo de integração de dados climáticos e de imagens na gestão agrícola

Abstract

Agriculture faces growing challenges due to climate change, which impacts the quality of produced grains. Extreme conditions, such as prolonged droughts and heavy rains, alter growth patterns and compromise crop health, resulting in lower yields, reduced nutritional value, and increased grain defects. To ensure sustainability and food security, it is crucial to adapt to these changes and seek innovative solutions for integrating climate data to enhance resilience and efficiency in agricultural management. Thus, this research was conducted with the aim of developing a model for integrating climate data and images to improve decision-making in agriculture. The adopted methodology included a literature review to identify gaps in existing knowledge about data integration. Based on this review, an integration model was developed using machine learning techniques to analyze data from weather stations

and grain images. The resulting model created a centralized repository, facilitating real- time access and analysis of information. The results showed that the integration of

climate data and images improves the accuracy of agricultural yield predictions and enables the evaluation of grain conditions considering various health states. The research included the practical capture and analysis of soybean grain images, documenting defects caused by climate variations, thus allowing for a precise assessment of plant health. Additionally, the integration model was tested in an agricultural traceability workflow, demonstrating its contribution to efficient monitoring in the sector. The use of an integrated system can optimize management practices such as irrigation and the application of agricultural inputs, resulting in improved productivity and product quality. Therefore, this research presents a practical model for application in agricultural management, promoting an efficient and adaptable approach to changing climatic conditions.