NOSES

The NOSES project develops an innovative solution to detect volatile organic compounds (VOCs) emitted by plants using advanced sensors and predictive models. The goal is to improve the management of downy mildew infections in crops such as grapevine and tomato by integrating digital and sustainable technologies.

The NOSES project aims to identify and classify volatile organic compounds (VOCs) associated with plant stress states through advanced algorithms, thereby improving the ability to detect and predict infections. A key objective is to develop an adaptive mathematical model capable of preventing secondary blight infections in crops such as grapevine and tomato. In addition, the project aims to validate these technologies in real-world scenarios, such as greenhouses and vineyards, with the ambitious goal of reducing the use of chemical treatments by 50 percent, making agricultural practices more sustainable and efficient.

The NOSES project integrates advanced technologies to provide innovative solutions in precision agriculture. Artificial intelligence (AI) and machine learning are used to analyze large amounts of data collected in the field, enabling the identification of complex patterns and accurately predicting the occurrence of infection or plant stress. IoT sensors, strategically deployed along the agricultural supply chain, monitor real-time environmental and physiological parameters, such as temperature, humidity and volatile organic compound (VOC) emissions. These data are processed by adaptive mathematical models, which are capable of autonomously updating themselves based on detected conditions, thus increasing the accuracy of predictions. Digital Decision Support Systems (DSS) integrate all information into a single platform, offering farmers simple but powerful tools to optimize crop management. Interoperability is provided by standardized APIs, which allow integration with other existing software and devices.