CropTypes - Crop Type Maps for Germany - Yearly, 10m

This raster dataset shows the main type of crop grown on each field in Germany each year. Crop types and crop rotation are of great economic importance and have a strong influence on the functions of arable land and ecology. Information on the crops grown is therefore important for many environmental and agricultural policy issues. With the help of satellite remote sensing, the crops grown can be recorded uniformly for whole Germany. Based on Sentinel-1 and Sentinel-2 time series as well as LPIS data from some Federal States of Germany, 21 different crops or crop groups were mapped per pixel with 10 m resolution for Germany on an annual basis since 2017. These data sets enable a comparison of arable land use between years and the derivation of crop rotations on individual fields. More details and the underlying methodology can be found in Gessner et al. 2025 and Asam et al. 2022.

Date (Creation): 2024-11-11T00:00:00

Edition: 2.0

Citation identifier: https://geoservice.dlr.de/catalogue/srv/metadata/4aeac9d6-935c-4fc4-a657-3c3296589b5f

Presentation form: Digital map

Purpose: These data sets enable a comparison of arable land use between years and the derivation of crop rotations and biodiversity. Such information is important for many environmental and agricultural policy issues. The data set fits to DLR's mission to address societal relevant information and to provide related products to decision makers and a broader public.

Status: ongoing

Author

German Aerospace Center (DLR) -

Point of contact

German Aerospace Center (DLR)

Maintenance and update frequency: As needed

Keywords

DLR
EOC
Germany
Crops
Agriculture
Random Forest Classification
Multispectral
Radar
Spectral Statistics
Temporal Statistics
Sentinel-1
Sentinel-2
IACS
opendata

Spatial scope

National

GEMET - INSPIRE themes, version 1.0

Agricultural and aquaculture facilities

Use limitation: Nutzungseinschränkungen: Das DLR ist nicht haftbar für Schäden, die sich aus der Nutzung ergeben. / Use Limitations: DLR not liable for damage resulting from use.

Access constraints: Other restrictions

Other constraints: Es gelten keine Zugriffsbeschränkungen

Use constraints: Other restrictions

Other constraints: Nutzungsbedingungen: Lizenz, https://creativecommons.org/licenses/by/4.0 / Terms of use: License, https://creativecommons.org/licenses/by/4.0

Other constraints: {"id": "cc-by-4.0",

"name": "Creative Commons Namensnennung - 4.0 International (CC BY 4.0)",

"url": " http://dcat-ap.de/def/licenses/cc-by/4.0 ",

"quelle": "Copyright DLR (year of production)"}

Spatial representation type: Grid

Denominator: 20000

Language: English

Character set: UTF8

Topic category

Farming

Begin date: 2017-03-01T00:00:00Z

End date: 2024-10-31T23:59:59Z

Unique resource identifier: EPSG:32632

Number of dimensions: 2

Dimension name: Column

Dimension size: 69845

Resolution: 10 m

Dimension name: Row

Dimension size: 100954

Resolution: 10 m

Cell geometry: Area

Transformation parameter availability: No

Distribution format

GeoTIFF ()

OnLine resource

CROPTYPES_DE_P1Y_V02 ( OGC:WMS )

EOC Land Map Service - Crop Type Maps for Germany

OnLine resource: HTTP Download Service ( WWW:LINK-1.0-http--link )

OnLine resource

EOC EO Products Service ( WWW:LINK-1.0-http--link )

EOC EO Products Service - STAC Collection: CROPTYPES_DE_P1Y_V02

OnLine resource: EOC Geoservice Dataset ( WWW:LINK-1.0-http--link )

OnLine resource

EOC Geoservice Map Context ( WWW:LINK-1.0-http--link )

EOC Geoservice Map Context (eoc:croptypes)

Hierarchy level: Dataset

Domain consistency

Measure identification: INSPIRE / Conformity_001

Conformance result

Date (Publication): 2010-12-08

Explanation: See the referenced specification.

Pass: Yes

Statement: Input data are all available Sentinel-1 and Sentinel-2 data of each respective year for the whole of Germany. LPIS data from several German Federal States are used.

Description: Processing: For details of processing see Gessner et al. 2025 and Asam et al. 2022. Temporal features of the employed remote sensing data and LPIS data were used in a Random Forest model to predict crop types. The classification result was post-processed using temporal and spatial filtering techniques and rule-based corrections.

Quality Assurance: Data quality is assured through a state of the art accuracy assessment. Annual overall accuracies range between 0.75-0.80.