Científicos Brasileños desarrollan una plataforma de IA para predecir la roya asiática de la soja

Brazilian scientists have developed a cloud-based AI platform to predict the risk of Asian rust in soybeans, integrating climate data, agronomic parameters, and leaf images. The system classifies the risk as low, medium, or high and provides management recommendations for more precise decision-making. Funded by FAPESP, UFSCar, and Embrapa, the platform uses hidden Markov chains, improving prevention and reducing fungicide use.

The Asian rust disease is one of the most damaging diseases affecting soybean crops. To address this challenge, Brazilian researchers have created an AI-driven platform that combines climate data, agronomic parameters, and digital leaf images to predict the risk of the disease's emergence. The cloud-based system generates technical management reports, enabling farmers to make more informed decisions about their operations.

The platform collects data from environmental sensors, digital images of soybean leaves, and agronomic parameters such as plant variety, row spacing, and planting schedules. The results are displayed on an online dashboard, allowing farmers to track seasonal climate conditions alongside plant images. This tool was developed under the "Advanced Digital Tool for Agricultural Risk Management" project, funded by the São Paulo Research Foundation (FAPESP).

The research was conducted as part of the doctoral work of computer scientist Ricardo Alexandre Neves at the Federal University of São Carlos (UFSCar), under the supervision of Paulo Cruvinel, a researcher at Embrapa Instrumentation in São Paulo. The project's findings were published in July 2025 in the journal AgriEngineering in the article "A cloud-based intelligence system for analyzing the risk of Asian rust in soybean crops."

The platform was built using data from field research, employing a model that integrates climate variables, soybean crop data, and information extracted from digital leaf images. Climate conditions were monitored throughout the observation period in the fields. "The technology classifies the susceptibility to the disease into three levels: low, medium, and high, based on the combination of these factors," explained the researchers.

By fusing diverse data sources, the system facilitates early diagnosis of the disease, allowing farmers to take preventive measures and reduce the use of fungicides. This innovative approach not only helps in managing the risk more effectively but also contributes to sustainable agricultural practices by minimizing chemical inputs. The platform's development represents a significant advancement in agricultural technology, offering a valuable tool for soybean farmers in Brazil and beyond.

The collaboration between FAPESP, UFSCar, and Embrapa highlights the importance of interdisciplinary research in addressing agricultural challenges. The successful integration of AI with climate and agronomic data demonstrates the potential of technology to support sustainable farming practices and improve crop resilience in the face of evolving pest threats. As the platform continues to be refined and adopted, it holds promise for enhancing the productivity and sustainability of soybean production in Brazil and other regions affected by Asian rust.