# IDTReeS 2020: Tree Crown Delineation and Species Classification in NEON Airborne Imagery (TACO)

## Facts

- Provider: Graves et al. (IDTReeS competition); TACO repackaging by ISP, Universitat de Valencia
- License: CC-BY-4.0 (https://zenodo.org/records/3934932)
- Size: 11 files
- Format: PNG (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/isp-uv-es/idtrees-taco
- Access: public, readable without an account
- DOI: https://doi.org/10.7717/peerj.16578
- Category: Earth Observation & Geospatial
- Source: https://huggingface.co/datasets/isp-uv-es/idtrees-taco
- Page: https://scigantic.com/archive/a418a802-0f6e-5231-847e-5bba43b683b3
- Keywords: Earth Observation & Geospatial, LiDAR, PNG, Hugging Face

## About

IDTReeS is the data science competition dataset for individual tree crown detection and species identification from National Ecological Observatory Network (NEON) Airborne Observation Platform data (PeerJ, 2023). This copy holds the training data for 85 field plots of 20x20 m at two NEON sites, each with a 0.1 m RGB orthophoto and a 1 m lidar canopy height model, and 1,312 hand-delineated crown polygons of which 1,213 are labelled with one of 33 field-identified taxa. The release's 369-band hyperspectral cube and LAS point clouds are not included, and the competition test set is a separate download. The train/validation split (68 and 17 plots) is assigned by plot by the repackagers. Small (about 37 MB) TACO archive read with tacoreader. Original competition data on Zenodo under CC BY 4.0; cite Graves et al. 2023.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="isp-uv-es/idtrees-taco", filename="assets/elliot.png", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: PNG

Example file: `assets/elliot.png`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/a418a802-0f6e-5231-847e-5bba43b683b3
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/a418a802-0f6e-5231-847e-5bba43b683b3
- Over MCP: `get_schema_card` with id `a418a802-0f6e-5231-847e-5bba43b683b3` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [PNG datasets](https://scigantic.com/topics/png)
- [LiDAR datasets](https://scigantic.com/topics/lidar)
