OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2

Abstract Our map represents the first successful large-area fusion of OpenStreetMap and Copernicus data at a spatial resolution of 10 m or finer and can be applied globally. We addressed varying label noise and feature space quality, utilizing artificial intelligence and advanced computing. Our meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Michael Schultz, Hao Li, Zhaoyan Wu, Daniel Wiell, Michael Auer, Zipf Alexander
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-04703-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190595260153856
author Michael Schultz
Hao Li
Zhaoyan Wu
Daniel Wiell
Michael Auer
Zipf Alexander
author_facet Michael Schultz
Hao Li
Zhaoyan Wu
Daniel Wiell
Michael Auer
Zipf Alexander
author_sort Michael Schultz
collection DOAJ
description Abstract Our map represents the first successful large-area fusion of OpenStreetMap and Copernicus data at a spatial resolution of 10 m or finer and can be applied globally. We addressed varying label noise and feature space quality, utilizing artificial intelligence and advanced computing. Our method relies solely on openly available data streams and methods, eliminating training data acquisition or the need for additional expert knowledge for such purpose. We extracted land use labels from OpenStreetMap and remote sensing data to create a contiguous land use map of the European Union as of March 2020. OpenStreetMap tags were translated into land use labels, directly mapping 61.8% of the Union’s area. These labels served as training data for a classification model, predicting land use in remaining areas. Country-specific deep learning convolutional neural networks and Sentinel-2 feature space composites of 2020 at 10 m resolution were employed. The overall map accuracy is 89%, with class-specific accuracies ranging from 77% to 99%. The data set is available for download from https://doi.org/10.11588/data/IUTCDN and visualization at https://osmlanduse.org .
format Article
id doaj-art-9d19dcabbbae4d42a93e372aed092ce6
institution OA Journals
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-9d19dcabbbae4d42a93e372aed092ce62025-08-20T02:15:14ZengNature PortfolioScientific Data2052-44632025-05-011211710.1038/s41597-025-04703-8OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2Michael Schultz0Hao Li1Zhaoyan Wu2Daniel Wiell3Michael Auer4Zipf Alexander5Geoinformatics of University of HeidelbergDepartment of Geography, National University of SingaporeZwsoft Co. Ltd.United Nations Food and Agriculture OrganizationHeidelberg Institute for Geoinformation TechnologyHeidelberg Institute for Geoinformation TechnologyAbstract Our map represents the first successful large-area fusion of OpenStreetMap and Copernicus data at a spatial resolution of 10 m or finer and can be applied globally. We addressed varying label noise and feature space quality, utilizing artificial intelligence and advanced computing. Our method relies solely on openly available data streams and methods, eliminating training data acquisition or the need for additional expert knowledge for such purpose. We extracted land use labels from OpenStreetMap and remote sensing data to create a contiguous land use map of the European Union as of March 2020. OpenStreetMap tags were translated into land use labels, directly mapping 61.8% of the Union’s area. These labels served as training data for a classification model, predicting land use in remaining areas. Country-specific deep learning convolutional neural networks and Sentinel-2 feature space composites of 2020 at 10 m resolution were employed. The overall map accuracy is 89%, with class-specific accuracies ranging from 77% to 99%. The data set is available for download from https://doi.org/10.11588/data/IUTCDN and visualization at https://osmlanduse.org .https://doi.org/10.1038/s41597-025-04703-8
spellingShingle Michael Schultz
Hao Li
Zhaoyan Wu
Daniel Wiell
Michael Auer
Zipf Alexander
OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
Scientific Data
title OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
title_full OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
title_fullStr OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
title_full_unstemmed OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
title_short OSMlanduse a dataset of European Union land use at 10 m resolution derived from OpenStreetMap and Sentinel-2
title_sort osmlanduse a dataset of european union land use at 10 m resolution derived from openstreetmap and sentinel 2
url https://doi.org/10.1038/s41597-025-04703-8
work_keys_str_mv AT michaelschultz osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2
AT haoli osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2
AT zhaoyanwu osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2
AT danielwiell osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2
AT michaelauer osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2
AT zipfalexander osmlanduseadatasetofeuropeanunionlanduseat10mresolutionderivedfromopenstreetmapandsentinel2