Tetteh et al. (2026) Nationwide annual agricultural land-use maps of Germany from 1990 to 2023 derived from satellite imagery
Identification
- Journal: Scientific Data
- Year: 2026
- Date: 2026-09-26
- Authors: Gideon Okpoti Tetteh, Vu-Dong Pham, Marcel Schwieder, Lukas Blickensdörfer, Alexander Gocht, Sebastian van der Linden, Stefan Erasmi
- DOI: 10.1038/s41597-026-08375-w
Research Groups
- University of Hamburg
- Thünen Institute
- German Federal Ministry of Agriculture, Food, and Regional Identity (BMLEH)
Short Summary
This study presents a dataset of nationwide annual agricultural land-use maps for Germany from 1990 to 2023, created using a deep learning approach based on Landsat and Sentinel-2 satellite images. The maps provide high-resolution information on the extent and type of agricultural land use, enabling long-term monitoring and analysis of agricultural landscape changes.
Objective
- To create a comprehensive dataset of annual agricultural land-use maps for Germany from 1990 to 2023 using remote sensing data.
- To evaluate the accuracy of the generated maps by comparing them with official agricultural statistics.
Study Configuration
- Spatial Scale: Nationwide, with a spatial resolution of 30 m.
- Temporal Scale: Annual, covering the period from 1990 to 2023.
Methodology and Data
- Models used: One-dimensional convolutional neural network (1D-CNN) for land-use mapping and land-cover classification.
- Data sources:
- Landsat images (1990-2023)
- Sentinel-2 images (2015-2023)
- Agricultural parcels declared by farmers in the GSA of CAP
- German-wide reference database used for GHG emissions calculation
Main Results
- The generated maps show high accuracy, with overall accuracies ranging between 85% and 93%.
- Dominant classes like grassland, rapeseed, winter cereals, sugar beet, and maize were detected with high accuracy (≥90%).
- Minor classes such as fallow land and plantation were predicted with low accuracy (≤52%).
Contributions
- The study provides a comprehensive dataset of annual agricultural land-use maps for Germany from 1990 to 2023.
- The maps can be used to fill temporal gaps in national agricultural statistics and to disaggregate those statistics to higher spatial units.
Funding
- This research was funded by the German Federal Ministry of Agriculture, Food, and Regional Identity (BMLEH) through the project "Development of a nationwide dataset of annual agricultural land-use maps for Germany".
- Additional funding was provided by the Thünen Institute.
Citation
@article{Tetteh2026Nationwide,
author = {Tetteh, Gideon Okpoti and Pham, Vu-Dong and Schwieder, Marcel and Blickensdörfer, Lukas and Gocht, Alexander and Linden, Sebastian van der and Erasmi, Stefan},
title = {Nationwide annual agricultural land-use maps of Germany from 1990 to 2023 derived from satellite imagery},
journal = {Scientific Data},
year = {2026},
doi = {10.1038/s41597-026-08375-w},
url = {https://doi.org/10.1038/s41597-026-08375-w}
}
Original Source: https://doi.org/10.1038/s41597-026-08375-w