NODES - SPOKE 6 Project VINO - D8.2 Report on the use of multi-source satellite images to the benefit of agriculture, on prediction models identified using temporal data acquired in other RM for resource optimization, and on optimization tools

The document explores the integration of remote sensing, artificial intelligence, and UAV-based monitoring to support sustainable viticulture in Northern Italy. Multi-source satellite imagery from Sentinel-1, Sentinel-2, and COSMO-SkyMed was used to develop advanced monitoring tools for vineyard health, biomass estimation, and phenological analysis. The Dual-Polarimetric Radar Vegetation Index (DpRVI) proved effective in capturing vineyard structural and seasonal variations, complementing optical indices such as NDVI. Deep learning models, particularly YOLOv8, were implemented to detect active and abandoned vineyards using high-resolution imagery, providing a scalable tool for land management. Additionally, NDVI time series and soil moisture data were employed to map the risk of Flavescence Dorée, a destructive vine disease. UAV-based NDVI mapping further enabled intra-plot variability assessment and vigor classification. Together, these approaches demonstrate the power of multi-sensor and predictive modeling for precision viticulture and climate-resilient agricultural management.

This document is part of the project NODES which has received funding from the MUR – Missione 4, Componente 2, Investimento 1.5 – Creazione e rafforzamento di “Ecosistemi dell’innovazione”, costruzione di “leader territoriali di R&S'' – del PNRR funded by the European Union - NextGenerationEU with grant agreement no. ECS00000036