Earth Observation monitoring and traffic lights tool

  1. Français non disponible
  2. English

This tool aims to demonstrate how the controls by monitoring can be implemented and deployed by exploiting Earth Observation (EO) data concerning eligibility criteria based on support schemes under control, concluding in traffic light codes at the parcel level. For achieving this objective, the output from EO classification engines such as the Sen4CAP will be matched with eligibility criteria coded as algorithms to produce a Decision Support System (NIVA – DSS) that will conclude in traffic light codes at the parcel level.

The tool has been tested for crop-specific payments for cotton and for specific voluntary coupled support schemes in Greece. When fully operational, a Business Rule Management System will be provided to allow users to build any desired eligibility criterion and the ones defined in its current application. This tool corresponds the EOs to the various crops on the field through artificial intelligence algorithms that train the EOs to recognise the crops correctly. IACS is involved in all stages of this application, but its contribution is essential in the initial training and re-training of the earth observation variables according to declarations.

The application will incorporate outcomes from third parties (registered apps – e.g. smartphone-based Geotagged Photos, registered FMISs or field books) to handle parcels assigned with a yellow traffic light. It will also incorporate data fusion techniques to enhance its capacity to handle large volumes of different datasets from an array of information sources. This data analysis process will improve the reliability and accuracy of the generated traffic lights with minimum human intervention.

Description of the use case
Relevance for monitoring and evaluation of the CAP

The tool serves the needs of control and checking and examines the farmers’ cross-compliance with pre-determined rules. It creates a database of crops grown in an area or Member State. Evaluators can re-use the data provided by crop type maps to serve many purposes.

First, these data can be used, together with other data sources and other EO tools, in estimating environmental indicators. For example, an evaluator can estimate irrigation water needs using crop type maps, soil maps, meteorological data, and agronomic information. The estimated irrigation water needs is a proxy for the ‘water use in agriculture’ impact indicator.

Second, crop type maps can evaluate the effects of agricultural policy measures on environmental indicators. For example, an evaluator can use IACS to get information on beneficiaries and non-beneficiaries of measures to reduce water consumption and compare their potential irrigation water needs.

Third, crop type maps are data sources that can cross-validate and triangulate information received from other sources. For example, a crop type map can cross-validate information related to policy effects on crop allocation and its consequent impacts on environmental indicators.

The examples above concern water but can be used for other indicators where prior knowledge of the grown crop is essential. For example, crop type maps can contribute, together with other data, to estimate indicators such as the potential nutrient use, the GHG emissions from managed soils, the soil erosion and soil organic matter, crop diversity, and others that depend on the type of soil cover.

The tool uses Sen4CAP data and develops algorithms and processes to produce, among others, detailed and accurate crop type maps. The tool is tested in Greece but is still at the development stage.

Conditions for using the tool: Its adoption in other regions will require adaptation and application of the algorithms and training to recognize the crop types of the region or the Member State. Adopting the tool assumes that the IT infrastructure is adequate and that the evaluator can manage and use the EO data. The functionality of EO data can be limited, in general, by several conditions. The most critical limitation is the extent of inconclusive parcels, i.e. parcels with no definite crop identification. Inconclusive parcels may be due to specific EO factors such as cloudiness or the prevalence of small parcels or stripes. Also, difficulties in training the algorithms that forecast crop type that may occur for specific crops. Finally, problems may arise in linking the crop type maps with the LPIS and IACS.

The evaluators who are interested in NIVA tools should consult the Action Plan for the uptake of NIVA tools: https://www.niva4cap.eu/wp-content/uploads/2021/08/D5.3.-Action-Plan-for-the-uptake-of-NIVA-tool-D1.0.pdf

 

Last modification date: 
08/12/2021