Project description
Crop monitoring under cloudy skies
Cloud cover poses a significant challenge to crop monitoring, as most tools rely on optical satellite data, which limits their use in regions with persistent clouds. With this in mind, the EU-funded DINOSAR project will develop algorithms that integrate optical, infrared, and Synthetic Aperture Radar (SAR) signals for continuous crop monitoring. Initially focusing on sugarcane in Colombia, the project’s approach will help farmers reduce their environmental footprint by providing reliable data throughout the growing season. This will enable more sustainable practices, matching agricultural inputs with actual crop needs. DINOSAR plans to revolutionise farming solutions based on Earth Observation (EO). It will also extend this methodology to other crops and geographies, making smart farming globally viable, rain or shine.
Objective
DINOSAR aims to develop Copernicus based algorithms to support smart farming applications that can be used worldwide, clouds, or no clouds. At the moment, most EO based crop monitoring tools are based on optical satellite inputs. In areas with substantial cloud cover the use of these applications is extremely limited. To be able to introduce more sustainable crop management practices, reliable and continuous time series on crop phenology and health throughout the growing season are needed. This will support farmers to match agricultural inputs (fertilisers, pesticides, water) with what the crop actually needs, decreasing their environmental footprint.
DINOSAR will do this by integrating the diagnostic power of optical, infrared and Synthetic Aperture Radar (SAR) signals. With the DINOSAR project we intend to kickstart a revolution in EO-based solutions that tackle challenges in agriculture (under clouds) by making full use of the Copernicus infrastructure. We intend to take the existing methodology a step further by designing a multi-sensor operational monitoring method for a single crop (sugarcane) capable of operating on large data volumes, and then extrapolating this approach to practical field cases and to other crops (and geographies) for which the application of EO-based applications has been underexplored. Rather than looking at optical and SAR based data as two parallel signals, we will focus on integrating the two early on in the processing chain. This has not been done before. Sugarcane in Colombia is our initial test-case, but we will not stop there. DINOSAR will also develop a methodology integrating the combined observations from optical, infrared and SAR EO satellites to monitor other crops in other geographies.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
- engineering and technologymechanical engineeringvehicle engineeringaerospace engineeringsatellite technology
- social sciencespolitical sciencespolitical transitionsrevolutions
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationsradio technologyradar
- agricultural sciencesagriculture, forestry, and fisheriesagriculture
- social scienceseconomics and businessbusiness and management
You need to log in or register to use this function
Programme(s)
Funding Scheme
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinator
6703 CT Wageningen
Netherlands
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.