Published May 4, 2023
| Version v1
Dataset
Open
Unlabeled Sentinel 2 time series dataset (training, T31TDJ): Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series
Authors/Creators
- 1. CESBIO - Centre d'études spatiales de la biosphère
Description
This is a part of the unlabeled Sentinel 2 (S2) L2A dataset composed of patch time series acquired over France used to pretrain U-BARN. For further details, see section IV.A of the pre-print article "Self-Supervised Spatio-Temporal Representation Learning Of Satellite Image Time Series" available here. Each patch is constituted of the 10 bands [B2,B3,B4,B5,B6,B7,B8,B8A,B11,B12] and the three masks ['CLM_R1', 'EDG_R1', 'SAT_R1']. The global dataset is composed of two disjoint datasets: training (9 tiles) and validation dataset (4 tiles).
In this repo, only data from the S2 tile T31TDJ are available. To download the full pretraining dataset, see: 10.5281/zenodo.7891924
| Dataset name | S2 tiles | ROI size | Temporal extent |
| Train |
T30TXT,T30TYQ,T30TYS,T30UVU, T31TDJ,T31TDL,T31TFN,T31TGJ,T31UEP |
1024*1024 | 2018-2020 |
| Val | T30TYR,T30UWU,T31TEK,T31UER | 256*256 | 2016-2019 |
Files
T31TDJ.zip
Files
(35.2 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:935fd221d1c6a6d1d97f46e412e877da
|
35.2 GB | Preview Download |
Additional details
Related works
- Is described by
- Preprint: https://hal.science/hal-04084839v1 (URL)
- Is referenced by
- Dataset: 10.5281/zenodo.7891924 (DOI)
- Is required by
- Software: https://src.koda.cnrs.fr/iris.dumeur/ssl_ubarn (URL)
Funding
- Agence Nationale de la Recherche
- DeepChange - Deep generative models for detecting land cover changes from satellite image times series ANR-20-CE23-0003