This long term partnership has proven to be a recipe for success, positioning Denmark as a trendsetter in public digitalisation and enabling full national scale operational use since 2019.

The CAP monitoring solution builds on DHI’s long standing expertise in satellite based agricultural monitoring. The technical backbone of the system is VeriCAP, which provides a streamlined, flexible, and accurate Check by Monitoring (CbM) and Area Monitoring System (AMS) solution. VeriCAP enables continuous monitoring of crop types and farm management practices in accordance with EU CAP rules and requirements, using Earth observation data combined with advanced image analysis techniques.

In 2019, the solution was successfully piloted at national scale in Denmark, demonstrating its capacity to monitor approximately 600,000 agricultural fields at 10 metre spatial resolution. Since 2020, the system has been fully operational as a running service, with satellite‑based information automatically integrated into the Danish Agricultural Agency’s IT systems and operational workflows. Today, it supports the administration of agricultural subsidy payments exceeding EUR 800 million annually. Denmark is widely regarded as a frontrunner in large‑scale implementation of satellite‑based CAP monitoring.

Together with the Danish Agricultural Agency, we have been among the first to establish a fully operational national‑scale system. At the same time, the Danish experience highlights that effective CAP monitoring solutions must be tailored to each country’s specific administrative practices, regulatory interpretations, and implementation models within the EU framework..

The approach has enabled the Agricultural Agency to harmonise existing monitoring frameworks, significantly reduce the need for physical field visits, increase effectiveness, and lower administrative costs. In recognition of its impact and its ability to exploit the potential of digitalisation to improve public administration, the solution received the Innovation Award at the Danish Digitalisation Awards in September 2021.

The project integrates multiple Earth observation data sources, including Sentinel 2 optical imagery, ICESat 2 altimetry, and sea surface height measurements from the SWOT mission, combined with machine learning models tailored to Arctic coastal environments.

A central innovation of EO4Hazards is the reconstruction of spatially varying tidal conditions using SWOT data, closing a long standing information gap in narrow fjords and near shore waters where conventional satellite altimetry and tide gauges are unavailable. These tidal estimates are used to correct and contextualise shallow water bathymetry products, enabling more robust identification of hazardous zones relevant for navigation.

The project focuses on selected areas along Greenland’s west coast, including fjords and coastal approaches where traditional hydrographic surveys are sparse or non existent. All workflows are designed for scalability, enabling rapid large area mapping that would be impractical using vessel based surveys alone.

EO4Hazards places strong emphasis on operational relevance. The generated products are tested and evaluated in collaboration with maritime authorities and operators, ensuring that outputs are fit for real world use and can be delivered in formats compatible with existing navigation and planning systems.

1) Quantify and qualify existing building resources by exploring the application of deep learning algorithms and a variety of EO data sources to systematically map, monitor and count different building objects with a view to estimate the availability of potentially reusable building material. The potential of such application could underpin new ways to adapt and built assets in line with circular principles for building design, thus contributing to reduce the carbon footprint of the construction industry and ultimately, reduce costs.

2) Improve building maintenance frameworks by exploring the application of deep learning technology and EO data sources to automatically monitor the health and condition of individual buildings as well as their surroundings. The intention of the activity is to explore the feasibility of deep learning and EO data to detect and map parameters such as, larger cracks in bricks, windows, pipes and facades; faded or peeling paint; vegetation overgrow; weathered, missing or damaged rooftop shingles; damaged solar cells and other relevant parameters.

• Monitoring critical infrastructure (e.g. detecting fallen trees or other obstacles on roads and railways, monitoring vegetation growth in the vicinity of electrical grids, detecting unapproved excavation work nearby power- and gas lines, monitoring soil moisture to detect waterpipe leaks, mapping flooded roads as well as general dynamic monitoring of traffic movement);
• Tracking and monitoring activity patterns and movement in operational scenarios (i.e., detecting and monitoring the number of people and cars to provide insight into activity patterns and early warnings for unusual activities);
• Monitoring the impact of emergency events (e.g. the extent of flooding’s and identification of people and housing impacted, monitoring fire risk and ongoing fire extent and movement, detecting and tracking oil spills, etc.).