# Greenhouse Strawberry Phenological Stage Detection: 1,477 Images with Seven Growth-Stage Classes and Fruit Size Ground Truth (University of Minnesota, AgML Mirror)

## Facts

- Provider: Qi Yang and Zhenong Jin (University of Minnesota); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://zenodo.org/records/10957909)
- Size: 12 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/strawberry_growth_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.10957909
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/strawberry_growth_detection
- Page: https://scigantic.com/archive/a3b414f9-6dcb-5709-a386-ba5f8558b9f0
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

Images of greenhouse strawberry plants grown under nitrogen treatments in 2022 and 2023, labeled with 3,997 bounding boxes across seven phenological stage classes for flower and fruit development, plus fruit-level size data from tagged fruits and a decimal growth stage. The original Zenodo release also holds treatment-level dry matter, fresh matter, fruit number and plant biomass tables, fruit condition classes (normal, wizened, malformed, overripe), and daily weather. It supports the paper predicting the growth trajectory and yield of greenhouse strawberries with knowledge-guided computer vision (Computers and Electronics in Agriculture 220, 108911). Useful for strawberry phenology detection, fruit growth modeling and yield prediction. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/strawberry_growth_detection") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Qi Yang and Zhenong Jin et al. and the DOI 10.5281/zenodo.10957909.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/strawberry_growth_detection")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00010.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/a3b414f9-6dcb-5709-a386-ba5f8558b9f0
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/a3b414f9-6dcb-5709-a386-ba5f8558b9f0
- Over MCP: `get_schema_card` with id `a3b414f9-6dcb-5709-a386-ba5f8558b9f0` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
