Speaker
Description
Understanding agro-ecosystem dynamics across spatial and temporal scales remains a major challenge in agricultural and environmental research. Experimental facilities and phenotyping platforms provide detailed observations of ecosystem processes and crop performance, while Earth Observation (EO) systems enable continuous monitoring across larger spatial extents. VITO has developed and operates a suite of complementary digital infrastructures (MAPEO, Terrascope, openEO, and CLIMTAG) that support the integration of drone, satellite, and meteorological observations. Together, these platforms help bridge the gap between experimental observations and landscape-scale monitoring.
At the field scale, MAPEO supports operational drone-based data acquisition and processing workflows. Recent developments enable the collection of millimetre-scale observations using low-cost drone systems, providing unprecedented detail on canopy architecture, plant traits, pests, diseases, and management effects. Emerging droneSTAC services facilitate interoperability with other research infrastructures.
At larger spatial scales, Terrascope provides cloud-based access to EO and climate datasets, while openEO offers a standardized processing interface that enables researchers to generate harmonized indicators without requiring expertise in cloud computing or geospatial infrastructure. These capabilities support research on vegetation dynamics, ecosystem functioning, environmental stress, and land-use patterns.
Building on these capabilities, CLIMTAG provides agri-climate indicators that help researchers to characterize environmental conditions, assess climate-related risks, and quantify stress events. These data provide essential context for interpreting ecosystem responses, investigating environmental drivers of observed patterns, and assessing resilience under past, current, and future climate conditions.
We present ongoing developments in satellite-drone data fusion, FAIR data sharing, cloud-native processing, and emerging AI-based services that facilitate the integration and analysis of complex geospatial datasets. By linking detailed local observations with regional-scale monitoring, these approaches enable more comprehensive investigations of agro-ecosystem functioning across sites, seasons, and environmental gradients while supporting scalable, interoperable, and FAIR research workflows.