# SEN12VTS: Sentinel-1 and Sentinel-2 Vegetation Time Series over Europe (2022-2023)

## Facts

- Provider: LINKS Foundation (Oldani et al.), GUARDIANS project
- License: MIT (https://huggingface.co/datasets/links-ads/sen12vts)
- Size: 479 files
- Stored at: Hugging Face, https://huggingface.co/datasets/links-ads/sen12vts
- Access: public, readable without an account
- Category: Earth Observation & Geospatial
- Source: https://huggingface.co/datasets/links-ads/sen12vts
- Page: https://scigantic.com/archive/c2bd15fa-6f22-56a0-bce8-fd3bc445ccfd
- Keywords: Earth Observation & Geospatial, satellite imagery, time series, Hugging Face

## About

SEN12VTS is a multi-sensor time-series dataset for NDVI regression and vegetation monitoring across Europe, built by LINKS Foundation for the GUARDIANS project. Bounding boxes of 512 x 512 pixels at 10 m were sampled where at least 90% of pixels fall in vegetated ESA WorldCover 2021 classes (tree cover, shrubland, grassland, cropland, wetland, mangroves), giving 1,166 non-overlapping boxes over 2022 and 2023 (36 only in 2022, 454 only in 2023, 676 in both), cropped to 256 x 256 tiles. Each box folder holds Sentinel-1 radiometrically terrain corrected (RTC) VV/VH GeoTIFFs split into ascending and descending orbits, Sentinel-2 L2A GeoTIFFs with 12 bands resampled to 10 m plus the scene classification layer (SCL), and a WorldCover raster. The full set is about 825 GB, served as 476 split tar.gz parts under data/ (concatenate and extract, then read with rasterio or xarray). Uses include NDVI reconstruction under cloud, SAR-to-optical fusion and vegetation time-series forecasting. Released under the MIT license by LINKS Foundation; use is also subject to the Copernicus Sentinel and ESA WorldCover data policies.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="links-ads/sen12vts", filename="data/sen12vts.tar.000.gz.part", repo_type="dataset")
print(path)
```

## Data structure

Example file: `data/sen12vts.tar.000.gz.part`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/c2bd15fa-6f22-56a0-bce8-fd3bc445ccfd
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/c2bd15fa-6f22-56a0-bce8-fd3bc445ccfd
- Over MCP: `get_schema_card` with id `c2bd15fa-6f22-56a0-bce8-fd3bc445ccfd` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [Time series datasets](https://scigantic.com/topics/time-series)
