# SSL4EO-L Benchmark: Landsat Land Cover (NLCD) and Crop Type (CDL) Segmentation

## Facts

- Provider: Stewart, Lehmann, Corley, Wang et al. (TorchGeo; UIUC, TUM, Microsoft AI for Good)
- License: CC0-1.0 (https://arxiv.org/html/2306.09424)
- Size: 13 files
- Stored at: Hugging Face, https://huggingface.co/datasets/torchgeo/ssl4eo_l_benchmark
- Access: public, readable without an account
- DOI: https://doi.org/10.48550/arXiv.2306.09424
- Category: Earth Observation & Geospatial
- Source: https://huggingface.co/datasets/torchgeo/ssl4eo_l_benchmark
- Page: https://scigantic.com/archive/80ff8abd-4c57-5076-8463-89f4b8ff98c8
- Keywords: Earth Observation & Geospatial, image segmentation, satellite imagery, benchmark, Hugging Face

## About

Semantic segmentation benchmark built for the SSL4EO-L paper (NeurIPS 2023) so that Landsat foundation models can be compared across five sensor products, including historical TM and ETM+ surface reflectance for which no labelled benchmark existed. Locations are sampled uniformly across the conterminous United States in a 60-day window centred on 1 August, when crops are easiest to tell apart, about 25,000 264x264 pixel patches per product at 30 m. Each patch is paired with a USDA Cropland Data Layer (CDL, 134 classes) mask and a USGS National Land Cover Database (NLCD, 17 classes) mask. Files are tar.gz archives per product and label set: ssl4eo_l_{tm_toa, etm_toa, etm_sr, oli_tirs_toa, oli_sr}_benchmark for imagery and ssl4eo_l_{tm, etm, oli}_{cdl, nlcd} for masks; about 48 GB. Nodata masks from ETM+ SLC-off imagery are copied into the labels. Load with torchgeo.datasets.SSL4EOLBenchmark. Released under CC0 1.0 per the paper's licensing appendix; cite Stewart et al. 2023.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="torchgeo/ssl4eo_l_benchmark", filename="ssl4eo_l_etm_cdl.tar.gz", repo_type="dataset")
print(path)
```

## Data structure

Example file: `ssl4eo_l_etm_cdl.tar.gz`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/80ff8abd-4c57-5076-8463-89f4b8ff98c8
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/80ff8abd-4c57-5076-8463-89f4b8ff98c8
- Over MCP: `get_schema_card` with id `80ff8abd-4c57-5076-8463-89f4b8ff98c8` 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)
- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
