The overall objective of CERES is to develop a set of geospatial information products affordable to any types of end-users designed to support information driven decisions in agriculture, increase profitability of the agricultural sector in Serbia and support Carbon Farming.
The set of products include: 1) identification of crop growth disturbance, 2) yield estimation, 3) estimation of soil organic carbon, 4) identification of tillage activities, 4) extracting information from web textual resources, 5) high resolution daily temperature and precipitation prediction. The information will be generated applying Artificial Intelligence (AI) methodologies to big geospatial data from various sources, primarily from open Earth Observation data (e.g. Copernicus Sentinel satellites), meteorological data (e.g. from meteo stations and meteo satellites), global soil data (e.g. from LandGis, SoilGrids), web textual sources and other available datasets. To train the robust models, a comprehensive in situ data on crop diseases/pests outbreaks, yields, soil organic carbon and tillage activities will be used, either from available sources (e.g. from previous projects) or collected within the scope of the CERES project.