Nationwide annual agricultural land-use maps of Germany from 1990 to 2023 derived from satellite imagery

Summary This is the data repository of our preprint (Tetteh et al., 2026), which is currently under review at Scientific Data. This repository contains the annual agricultural land-use (LU) maps of Germany from 1990 to 2023, created from a time series of Landsat and Sentinel-2 images using the deep learning approach described in Pham et al. (2024). Each LU map contains 14 LU types, namely winter cereals, summer cereals, maize, grassland, potato, sugar beet, rapeseed, sunflower, legumes, horticultural crops, fallow land, vineyards, hops, and plantations. This dataset provides a consistent, spatially explicit record of agricultural land use over more than three decades and can support studies of agricultural change, land-use dynamics, biodiversity, ecosystem services, climate impacts, and agricultural policy evaluation. Data Contents This repository contains a zipped file called “HCTM_Data.zip”. Within this zipped file, there are two folders named “LU_Maps” and “CSO_Maps”. The “LU_Maps” folder comprises 34 cloud-optimized GeoTIFF (COG) images, corresponding to the agricultural LU maps from 1990 to 2023. Each image is named according to the format “HCTM_GER_[year]_rst_v101_COG.tif”. For each LU map, there is a corresponding clear-sky observation (CSO) map named “CSOS_GER_[year]_rst_v101_COG.tif” in the “CSO_Maps” folder. Each LU map contains a single band, and each pixel per band contains a positive integer value representing the agricultural LU type. Interpretation of the pixel values can be found in the color table files “HCTM_GER_LegendEN_rst_v101.clr” (English version) and “HCTM_GER_LegendDE_rst_v101.clr” (German version), which are located in the “LU_Maps” folder. In the color table, the first column represents the pixel value, the second to the fifth columns represent the RGBA color format, and the last column is the agricultural LU type. Each pixel in a CSO image contains 12 bands, representing the 12 months (January to December) of a year. Each CSO band contains the total number of CSOs per month of a year. Methods Annual training samples were extracted from farmer-reported crop declarations collected between 2006 and 2022. Satellite image time series from Landsat and Sentinel-2 were preprocessed with the Framework for Operational Radiometric Correction for Environmental Monitoring (FORCE) (Frantz, 2019) to generate analysis-ready data (ARD), which were used to train a multi-year one-dimensional convolutional neural network (1D-CNN). The trained model was subsequently applied to classify annual agricultural LU types across Germany for the entire study period. For more details about the methods, we refer readers to our preprint (Tetteh et al., 2026). Version Version v101: This is the initial release based on our aforementioned preprint. Any updates to the maps would result in newer versions being uploaded to this repository. How to cite Dataset: cite this repository (see example below). To see various citation styles provided by Zenodo, see the right-hand side of this page under the “Citation” section. Tetteh, G. O., Pham, V.-D., Schwieder, M., Blickensdörfer, L., Gocht, A., van der Linden, S., & Erasmi, S. (2026). Nationwide annual agricultural land-use maps of Germany from 1990 to 2023 derived from satellite imagery (Version v101) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.20815677 Paper: the aforementioned preprint must be cited as the paper underpinning the dataset. The citation below, which is subject to change once the paper is finally published in a journal, could be used: Tetteh, G. O., Pham, V.-D., Schwieder, M., Blickensdörfer, L., Gocht, A., Linden, S. van der, & Erasmi, S. (2026). Nationwide annual agricultural land-use maps of Germany from 1990 to 2023 derived from satellite imagery. Research Square. https://doi.org/10.21203/rs.3.rs-9074257/v1 Funding This dataset was generated within the Nationwide Monitoring Program of Biodiversity in Agricultural Landscapes (MonViA) project, which is funded by the German Federal Ministry of Agriculture, Food, and Regional Identity (BMLEH).