Unlabeled Sentinel 2 time series dataset (training, T30TYQ): Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series

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 T30TYQ are available. To download the full pretraining dataset, see: 10.5281/zenodo.7891924

Global unlabeled dataset description

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