# RapidAI4EO: A Corpus of Dense Time Series Satellite Imagery

The RapidAI4EO corpus is a dataset of dense time series satellite imagery sampled at 500,000 locations across Europe.
Sample locations are non-overlapping with a footprint of 600×600 metres.
At each location the corpus contains datacubes of two cloud-free, regular-cadence image products and corresponding land cover labels:

* Planet Fusion three-metre, five-day cadence radiometrically harmonized and gap-filled imagery for 2018–2019
* Sentinel-2 L2A monthly image mosaics at 10-metre resolution for 2018
* CORINE Land Cover multiclass labels for 2018

Originally designed to train deep learning models for land use and land cover (LULC) classification and change detection, the corpus is being released as open data to support research in these domains as well as others that could benefit from dense time series satellite imagery.

The corpus was created under the [RapidAI4EO](https://rapidai4eo.eu/) project, which received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101004356.


## Download Dataset

This dataset is hosted at the URL `https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/` on Azure Blob Storage. Labels can be found within the `labels` sub-directory and imagery can be found within the `imagery` sub-directory. A complete static [STAC](https://stacspec.org) catalog for the dataset is found within the `stac-v1.0` sub-directory. It's recommended to use [AzCopy](https://learn.microsoft.com/en-us/azure/storage/common/storage-use-azcopy-v10) to download the dataset. For example, to download the labels using AzCopy, you can run the following command:

```
azcopy copy --recursive https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/labels/ .
```


## Dataset Licenses

* Planet Fusion: [CC-BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/)
* Sentinel-2: [Copernicus Sentinel Data Terms and Conditions](https://sentinel.esa.int/documents/247904/690755/Sentinel_Data_Legal_Notice)  
* CORINE Land Cover: [Registration and Licensing Conditions of the European Parliament and of the Council on the European Earth monitoring programme](https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A32013R1159)


## Links

* [STAC Browser](https://radiantearth.github.io/stac-browser/#/external/radiantearth.blob.core.windows.net/mlhub/rapidai4eo/stac-v1.0/catalog.json)
* [Documentation](https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/documentation.pdf)
* Tutorial, comprised of the following files:
    * [Jupyter notebook file](https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/tutorial/tutorial.ipynb)
    * [Supporting Python file](https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/tutorial/rapidai4eo.py)
    * [Jupyter notebook file exported as HTML](https://radiantearth.blob.core.windows.net/mlhub/rapidai4eo/tutorial/tutorial.html)


## Authors

* Timothy Davis
* Benjamin Bischke
* Patrick Helber
* Caglar Senaras
* Akhil Rana
* Annett Wania
* Ruben Van De Kerchove
* Daniele Zanaga
* Wanda De Keersmaecker
* Myroslava Lesiv
* Franck Ranera
* Giovanni Marchisio


## Citation & DOI

Davis, T., Bischke, B., Helber, P., Senaras, C., Rana, A., Wania, A., Van De Kerchove, R., Zanaga, D., De Keersmaecker, W., Lesiv, M., Ranera, F., & Marchisio, G. (2023) "RapidAI4EO: A Corpus of Dense Time Series Satellite Imagery", Version 1.0, Radiant MLHub. [Date Accessed] [https://doi.org/10.34911/RDNT.GCYDKJ](https://doi.org/10.34911/RDNT.GCYDKJ)

In BibTeX format:

```
@dataset{rapidai4eo,
  title = {RapidAI4EO: A Corpus of Dense Time Series Satellite Imagery},
  publisher = {Radiant ML Hub},
  doi = {https://doi.org/10.34911/RDNT.GCYDKJ},
  year = {2023},
  urldate = {<date of access, ISO>},
  author = {
    Davis, Timothy and
    Bischke, Benjamin and
    Helber, Patrick and
    Senaras, Caglar and
    Rana, Akhil and
    Wania, Annett and
    Van De Kerchove, Ruben and
    Zanaga, Daniele and
    De Keersmaecker, Wanda and
    Lesiv, Myroslava and
    Ranera, Franck and
    Marchisio, Giovanni
  },
  version = {1.0},
}
```