Objectives of the service
Farmers across Europe must verify sustainable practices to access carbon programs and meet supply chain demands. Currently, this process, identifying crop types, sowing and harvesting dates, and tillage practices s manual, costly, and error-prone. eAgronom addresses this by developing a satellite-based monitoring service that automates the detection of main and cover crops, determines sowing and harvesting times, and classifies tillage type as conventional, reduced, or no-till.
Using Sentinel-1 and Sentinel-2 data combined with machine learning, the service provides reliable, regionally adaptable insights directly through eAgronom’s farm management platform. This reduces farmer workload, improves data accuracy, and enables transparent, scalable monitoring across Europe.
The activity aims to validate and demonstrate this solution in real-world conditions, involving pilot farmers and progressing toward a commercial-grade, fully integrated verification system.
Users and their needs
The service targets crop farmers in Estonia, Latvia, Lithuania, Poland, Romania, Moldova, Spain, Czech Republic, and Ukraine who are enrolled in carbon or sustainability programs and use eAgronom’s farm management platform. These users must verify the adoption of sustainable practices—such as cover cropping, reduced tillage, and optimal crop rotations—to qualify for carbon credits or meet the environmental criteria of food supply chains and financial institutions. Their key needs include: reliable detection of both main and cover crops from satellite imagery; accurate determination of sowing and harvesting dates; classification of tillage practices (conventional, reduced, or no-till); the ability to manually input agricultural practices when satellite data is insufficient; and identification of inconsistencies between reported practices and satellite-derived data. The core challenge for the project is to deliver accurate, scalable remote sensing models that perform consistently across diverse
agro-climatic regions and farming systems. Differentiating between cover crops and winter cereals, achieving high model confidence, and ensuring a seamless user experience for farmers are central to meeting these needs and supporting widespread adoption.
Service/ system concept
The service provides farmers with clear, field-level information on whether cover crops and main crops were grown, when fields were sown and harvested, and what type of tillage was used (conventional, reduced, or no-till). This data is delivered automatically and visually through the farmer’s existing eAgronom platform, helping them meet requirements for carbon programs and sustainable food supply chains. If satellite detection isn’t possible, farmers can manually enter their practice data.
The system works by combining satellite images (from Sentinel-1 and Sentinel-2), weather and soil data, and machine learning models trained on real farm data. When a farmer draws their field on the map, the system automatically analyses the satellite images over time and returns verified results about what happened on that field and when.
At a high level, the system collects satellite and environmental data, processes it in the cloud, runs it through trained models, and displays the results in a simple dashboard. Farmers can see insights for each of their fields and resolve any data conflicts easily.
Space Added Value
The service uses Sentinel-1 (radar) and Sentinel-2 (optical) satellites from the Copernicus program. Sentinel-1 is particularly valuable because it can capture data regardless of cloud cover or daylight, making it ideal for frequent monitoring even in poor weather. Sentinel-2 provides high-resolution optical imagery that helps identify vegetation health and crop development over time.
By combining both radar and optical data, the system can accurately detect cover crops, main crops, sowing and harvesting events, and tillage practices across diverse climates and soil types. This dual-source approach increases reliability and precision compared to traditional methods, which rely heavily on manual field visits, farmer-reported data, or single-source imagery that is often obstructed by clouds.
Compared to existing competitors, the use of frequently updated Copernicus satellite data allows for scalable, cost-effective monitoring across millions of hectares. This reduces the burden on farmers, increases trust from carbon certifiers and food companies, and lowers verification costs. The added value is a highly automated, precise, and regionally adaptable system that outperforms manual verification or single-sensor solutions, enabling broader adoption of sustainable farming practices.
Prime Contractor(s)
Subcontractor(s)
