Project abstract:
Agrochemical application constitutes one of the most important agricultural practices. Indeed, it is almost impossible to reach high yields from both quantitative and qualitative points of view if this practice is executed correctly. Modalities and machinery used to perform this task considerably influence treatment efficiency, farm production costs, workplace safety, and ecosystem durability. In this context, this proposal aims to investigate the quality and sustainability of mechanical application of agrochemicals in olive orchards, considering spray distribution evenness, environmental impact and workers’ and bystanders’ safety. Particularly, the project will focus on the development of an innovative and smart tool, a “Digital Tree” (DT), which allows predicting spray behavior under different operations and field conditions and, consequently, improving the application of Plant Protection Products (PPPs), considering both technical and environmental aspects. This implies an accurate knowledge of equipment mechanical features, functioning and regulations, field and crop features, and climatic conditions.
Hence, to pursue the objective above, quantitative and qualitative evaluation of the spray, including foliar deposition, ground losses, drift, and environmental impact based on life cycle assessment, will be evaluated by implementing international standards and methodologies. In addition, sensing technologies and machine learning techniques will be implemented to collect data and build predictive spray models under different conditions. This will enable the setting up of the most suitable operation parameters according to the implemented equipment and improve its technical performance. Once the “Digital Tree” is built, it would be possible to optimize crop protection for a more accurate, targeted, and sustainable agrochemical application through the improvement of a series of operational and managerial parameters.

keywords: Machine learning; Smart technologies; Equipment; Spray quality; Olives; Sustainability;

Announcement  PRIN 2022 PNRR funding MUR Ministry of University and Research

Reference Group: Trustworthy and Explainable Machine Intelligence

Partners: University of Catania (UniCT), Institute of High Performance Computing and Networks of the National Research Council (ICAR-CNR), Mediterranean University of Reggio Calabria (UniRC)

Geographic scope: National

Project Coordinator: Giovanni Costa

Start date: 30 November 2023

End date: 30 June 2026

Project website: https://sites.google.com/icar.cnr.it/prin2022pnrr/