The DLR CropTypes maps are raster data sets that display the cultivated main crop in Germany per year since 2017.

The analysis is based on temporal features (monthly statistics) of gap-filled Sentinel-2 and Sentinel-1 images time series. The overall 336 temporal features (264 optical and 72 radar features) are used together with reference data generated from LPIS data sets from some German Federal States in a Random Forest model. Non-cropland areas are masked based on a mask generated from official and OSM land cover data. The classification result is post-processed using temporal and spatial filtering techniques and rule-based corrections. More details and the underlying methodology can be found in Gessner et al. 2025 and Asam et al. 2022.

The dataset is provided in the format of 8-bit Cloud Optimized GeoTiff files in the WGS 1984 UTM (Zone 32N) projection (EPSG:32632), with a pixel size of 10 m and each file covering the whole of Germany.

The legend specifying the meaning of the class code is given in  "LEGEND_CropTypes_Germany.txt"

The CropTypes maps are licensed under CC-BY-4.0.

When using this data set, please refer to: 

Gessner, U.; Hirner, A.; Asam, S.; Wenzl, M.; Kuenzer, C. Combining Machine Learning and Spatio-Temporal Filtering to Map Crop Types of Germany for Seven Years. IEEE Geosciences and Remote Sensing Letters, 2025, 22, 2504805. DOI: 10.1109/LGRS.2025.3587517

Asam, S.; Gessner, U.; Almengor González, R.; Wenzl, M.; Kriese, J.; Kuenzer, C. Mapping Crop Types of Germany by Combining Temporal Statistical Metrics of Sentinel-1 and Sentinel-2 Time Series with LPIS Data. Remote Sens. 2022, 14, 2981. https://doi.org/10.3390/rs14132981

For further information please contact: ursula.gessner@dlr.de