DIONE SIGNED

Project "DIONE" data sheet

The following table provides information about the project.

 Partnership

Take a look of project's partnership.

Map

 Project objective

DIONE proposes a close-to-market (TRL7) area-based direct payments monitoring toolbox that will address the forthcoming Modernised CAP regulation of using automated technologies to ensure more frequent, accurate and inexpensive compliance checks. In particular, DIONE will: (i) Capitalise on recent results of ESA’s SEN4CAP project that showcased the capability of Sentinel data to monitor the crop diversification rules. DIONE shall further integrate generated crop-type maps in a way directly exploitable by the paying agencies; (ii) Include in the analysis the so far neglected EFA types (fallow land of all sizes, buffer strips, hedges, trees), by making use of super-resolution technology that improves the 10-20m Sentinel resolution to an improved resolution range (5-10m). This is enabled through Machine-Learning (ML) based post-processing and data fusion of Copernicus DIAS-sourced data with targeted drone-obtained data. This aims to motivate the use of such EFAs over the –of ambiguous environmental impact- use of productive areas (nitrogen-fixing crops and catch crops). (iii) Complement the use of EO data with a system of reliable, ground-based geo-tagged photos, captured by the farmers that exploits (a) advances that allow for improved positional accuracy, (ii) low-footprint encryption techniques for improved data security and reliability and (iii) image detecting manipulation techniques (image forensics). The system will allow for an improved LC/LU annotation and ensure the process is untampered. (iv) Implement a Green Compliance toolbox, integrated with the paying agencies’ aforementioned tools. This will benefit from (a) low-cost spectral sensors measuring soil quality and assessing the status of land-degradation in the land parcels and (b) an ML-based inferencing system deployed on a larger scale (regional, national) to quantify the levels of some of the monitored parameters and consequently extract tangible environmental performance metrics for an entire region