TimeSen2Crop: One Million Labelled Sentinel-2 Pixel Time Series for Crop Type Classification, Austria (TACO)
- Provider
- Weikmann, Paris, Bruzzone (University of Trento); TACO repackaging by ISP, Universitat de Valencia
- License
- CC-BY-4.0 (source)
- Size
- 9 files
- Format
- PNG (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/isp-uv-es/timesen2crop-taco)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.1109/JSTARS.2021.3073965
- Category
- Agriculture & Environment
- Source
- https://huggingface.co/datasets/isp-uv-es/timesen2crop-taco
About this dataset
TimeSen2Crop (IEEE JSTARS, 2021) is a pixel-level crop type classification benchmark of 1,135,511 labelled Sentinel-2 pixel time series over Austria, drawn from 15 Sentinel-2 tiles that cover the country's agro-ecological zones. Labels come from Austrian agricultural parcel declarations for the agronomic year starting September 2017 and span 15 crop classes, with per-class counts checked against the release's description PDF. Each series has nine bands (B2, B3, B4, B5, B6, B7, B8A, B11, B12) gap-filled to a daily 365-step cadence. In this TACO copy one sample is one tile, with pixels packed into the raster grid, so a leaf must be reshaped to time by band by pixel rather than treated as an image. The release's five cross-validation folds are tile partitions and are carried as a test_fold field; legend and band names were checked against the release's PDF. About 11.5 GB, read with tacoreader. Original on Zenodo under CC BY 4.0; cite Weikmann et al. 2021.
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="isp-uv-es/timesen2crop-taco", filename="assets/logos.png", repo_type="dataset")
print(path)Data structure
File types in sampled files: PNG
Files
Example file: assets/logos.png
Analyze this dataset without downloading it
On Scigantic, TimeSen2Crop: One Million Labelled Sentinel-2 Pixel Time Series for Crop Type Classification, Austria (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 Agriculture & Environment datasets
- Banana Bunch Detection Images from Four Fields in Madeira, Portugal: 2,179 Smartphone Photos with 3,718 Boxes (Universidade da Madeira, AgML Mirror)
- WE3DS: RGB-D Stereo Images of Crops and Weeds with Hand-Annotated Semantic Segmentation Masks, 2,568 Images (BOKU Vienna, AgML Mirror)
- Soil E. coli Survival and Transfer to Cucumbers under Poultry Litter Amendments and Plastic Mulch: 2018 and 2019 Field Trials, Delaware (USDA ARS; Food AI Nexus Curation)
- Annotated Food Crop and Weed Images for Robotic Vision: 1,176 Images of 6 Crops and 8 Weed Species with 7,853 Boxes (AgML Mirror)
- OliveTreeCrownsDb: High-Resolution UAV Images of Olive Orchards with 66,950 Tree Crown Bounding Boxes (Sidi Mohamed Ben Abdellah University, AgML Mirror)
- Clay v1.5 NAIP-2
- AI4SmallFarms: Smallholder Crop Field Boundary Delineation from Sentinel-2, Vietnam and Cambodia (TACO)
- Litchi-UAV: Drone Images of Litchi Fruit in Dense Canopies with 39,415 Bounding Boxes, Guangzhou, China (AgML Mirror)