In monitoring and auditing, crop type maps are used to assess compliance with various rules. They can be used in controls and inspections, especially to guide smart sampling. SENSAGRI distinguishes between irrigated and non-irrigated arable land, produces early maps, and replicates the maps through the cultivation period.
In evaluation, SENSAGRI’s cultivated crop type maps can become an essential tool for three reasons. First, their high resolution can provide a detailed spatial allocation of crops more finely and precisely than CORINE for all farmers in an area, including beneficiaries and non-beneficiaries of various measures. This information can be used, together with ancillary data 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, these maps, together with IACS data, can evaluate specific environmental indicators at the farm level. For example, since these maps distinguish between irrigated and non-irrigated plots, they can estimate irrigation water needs for a wider area. These maps can support the evaluation of the impacts of policy interventions at the landscape level. Changing crop type spatial allocation and preserving non-productive features may result from policy measures, especially if these areas fall within the boundaries of Natura 2000 or River Basins. 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 Seasonal Crop Maps validation process was performed in three different European test sites (South of France, North of Spain and South of Italy). The added-value crop map validation process was performed in the test site of Castilla y León. The tool was validated at the proof-of-concept stage, and it is feasible to take to the commercialisation stage.
Conditions for use:
When applied to another region or Member State, the tool requires calibration so that their Artificial Intelligence (AI) algorithms are trained to recognise the crops of the new region. The calibration of the seasonal crop map is more straightforward since it does not require access to the detailed in situ data needed by the value-added map. The value-added map requires a connection with IACS and field visits. Adopting the tool assumes that the IT infrastructure is adequate and that the evaluator can use the data. The usual EO caveats hold. For this tool, the most critical limitation is the extent of inconclusive parcels, i.e. parcels for which there is no definite crop identification. Inconclusive parcels may be due to specific EO factors such as cloudiness or the prevalence of small parcels and also may be due to difficulties in training the algorithms to attain very high correct forecasts.
