Green cover algorithm

Netherlands Enterprise Agency

Detecting green cover on arable land.

Last change on 18th of July 2025, at 11:49 (CET) | Publication Standard 1.0

• Publication category: Impactful algorithms
• Impact assessment: DPIA
• Status: In use

General information

Theme

Nature and Environment

Begin date

2023-01

Contact information

https://www.rvo.nl/onderwerpen/contact/formulier

Link to publication website

https://www.rvo.nl/onderwerpen/glb-2024/ams

Responsible use

Goal and impact

The algorithm helps make the annual CAP grant application better. It checks whether the applicant's information is correct. If something is incorrect, the applicant is notified.

Considerations

Since 2023, the Area Monitoring System (AMS) has been mandatory for monitoring land-related schemes. This is stated in Article 7 of a European law (EU 2022/1173). Using satellite images is the most efficient way to do this automatically. The applicant can also provide their own evidence and may later object if they disagree with something.

Human intervention

If the algorithm finds a discrepancy, an employee first looks at the result. If the clerk agrees with the deviation, he will let the requester know. The applicant can then send evidence via a special app (the geotag photo app) to show that it might be right after all.

Risk management

The quality of the algorithm is tested annually. This is done on the basis of samples. And a mandatory quality test that has to be reported to the European Commission.

Legal basis

Since 2023, the Area Monitoring System (AMS) has been a mandatory component for monitoring land-based schemes, as stipulated in Article 7 of Implementing Regulation (EU) 2022/1173.

Links to legal bases

UITVOERINGSVERORDENING (EU) 2024/2202 VAN DE COMMISSIE van 4 september 2024 : https://eur-lex.europa.eu/legal-content/NL/TXT/PDF/?uri=OJ:L_202402202

Impact assessment

Data Protection Impact Assessment (DPIA)

Operations

Data

Functional_id, declared crop code, geometry, application number (declaration of relationship data for a CAP grant application, Satellite data).

Links to data sources

• BRP Gewaspercelen : https://www.pdok.nl/-/brp-gewaspercelen
• Copernicus Data Space Ecosystem : https://dataspace.copernicus.eu/

Technical design

The green cover marker detects green cover during defined periods of time. The green cover marker uses the NDVI (Normalised Difference Vegetation Index), analysing both the raw NDVI data and a smoothed version (via a Savitzky-Golay filter). A plot is considered vegetated when the smoothed signal exceeds a threshold value of 0.2 during the analysis period. Two types of events are distinguished: Type-1 (high probability) where both the raw and smoothed signal exceed the threshold, and Type-2 (low probability) where only the smoothed signal does so. Neighbouring observations that meet these criteria are grouped into a single event. A mechanism is built in to extend Type-2 events if they are directly adjacent to Type-1 events, to better capture realistic vegetation periods.

The reliability of a vegetation event is determined based on the average NDVI signal during the event. If the mean of the raw observations is above 0.2, the base reliability is 0.5 and an additional component is added depending on how strong the mean signal is above the threshold. If the mean is not above 0.2, a lower base reliability (0.25) applies and the additional component is determined based on the smoothed signal. In a new variant of the marker, based on PF data, observations above the threshold are grouped into events, with a minimum duration of two days. Here, linear interpolation is applied if no direct observations are available, although this can sometimes lead to inaccuracies (artefacts).

This is not a self-learning algorithm.

External provider

NEO BV