Dataset Open Access

A new remote sensing benchmark dataset for machine learning applications : MultiSenGE

Romain Wenger; Anne Puissant; Jonathan Weber; Lhassane Idoumghar; Germain Forestier

David Michea

MultiSenGE is a new large-scale multimodal and multitemporal benchmark dataset covering one of the biggest administrative region located in the Eastern part of France. It contains 8,157 patches of 256 * 256 pixels for Sentinel-2 L2A, Sentinel-1 GRD and a regional LULC topographic regional database. 

Every file has a specific nomenclature :

  • Sentinel-1 patches: {tile}_{date}_S1_{x-pixel-coordinate}_{y-pixel-coordinate}.tif
  • Sentinel-2 patches: {tile}_{date}_S2_{x-pixel-coordinate}_{y-pixel-coordinate}.tif
  • Ground reference patches: {tile}_GR_{x-pixel-coordinate}_{y-pixel-coordinate}.tif
  • JSON Labels: {tile}_{x-pixel-coordinate}_{y-pixel-coordinate}.json

where tile is the Sentinel-2 tile number, date the date of acquisition of the patch, x-pixel-coordinate and y-pixel-coordinate are the coordinates of the patch in the tile.

In addition, you can find a set of useful python tools for extracting information about the dataset on Github :

First experiments based on this dataset is in press in MultiSenGE : A Multimodal And Multitemporal Benchmark Dataset For Land Use/land Cover Remote Sensing Applications, XXIV ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (Nice, 2022).

Due to the large size of the dataset, you will only find the associated JSON files on this Zenodo repository. To download the Sentinel-1, Sentinel-2 patches and the reference data, please do so via these links: 

Files (8.5 MB)
Name Size
8.5 MB Download
All versions This version
Views 8282
Downloads 22
Data volume 17.0 MB17.0 MB
Unique views 6969
Unique downloads 22


Cite as