IDTReeS 2020: Tree Crown Delineation and Species Classification in NEON Airborne Imagery (TACO)
- Provider
- Graves et al. (IDTReeS competition); TACO repackaging by ISP, Universitat de Valencia
- License
- CC-BY-4.0 (source)
- Size
- 11 files
- Format
- PNG (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/isp-uv-es/idtrees-taco)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.7717/peerj.16578
- Category
- Earth Observation & Geospatial
- Source
- https://huggingface.co/datasets/isp-uv-es/idtrees-taco
About this dataset
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.
How to load this dataset in 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
Files
Example file: assets/elliot.png
Analyze this dataset without downloading it
On Scigantic, IDTReeS 2020: Tree Crown Delineation and Species Classification in NEON Airborne Imagery (TACO) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Earth Observation & Geospatial datasets
- ESA WorldCover Sentinel-1 and Sentinel-2 10m Annual Composites
- Soft Commodity Infrastructure
- SSL4EO-S12 (v1.0): Large-Scale Multimodal Multitemporal Sentinel-1/2 Pretraining Dataset
- Land Cover Datasets
- Trazo Field Boundary Annotations (fiboa)
- LandCoverNet Australia: Annual Land Cover Labels on Sentinel-1, Sentinel-2 and Landsat-8 Time Series (2018)
- Digital Earth Africa GeoMAD
- Digital Earth Africa Coastlines: S3 inventory files