# OPheno Curated Weed Emergence and Phenology Dataset: Field Trial Observations of Weed Seedling Emergence and BBCH Growth Stages in European Crops

## Facts

- Provider: OPheno initiative and contributing organizations
- License: CC-BY-4.0 (https://huggingface.co/datasets/OPheno/Weed-phenology)
- Size: 6 files
- Format: PNG, CSV (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/OPheno/Weed-phenology
- Access: public, readable without an account
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/OPheno/Weed-phenology
- Page: https://scigantic.com/archive/b3ad0fa6-1293-5499-9b8d-cd0d8c977d40
- Keywords: Agriculture & Environment, PNG, CSV, Hugging Face

## About

A harmonized table of weed emergence and phenology observations gathered from field trials, greenhouse experiments and published studies, curated by the OPheno initiative to support weed emergence timing models, phenology models and integrated weed management decision tools, and expanded as new submissions are reviewed. The current release holds 14,615 observations from 56 trials in ten countries (Denmark, Spain, Iran, Italy, Latvia, Norway, Poland, Portugal, Sweden and Turkey) covering seven target weed species in three crops, with crops and weeds named by EPPO codes. Each row gives the trial, crop establishment method, tillage system, trial type, seeding date, observation date, assessment type (for example cumulative seedling emergence percentage or BBCH growth stage), value and unit, site latitude and longitude, photoperiod, day of year, days after seeding, contributor and organization. Data are one CSV file (train.csv, about 4 MB) loadable with pandas, R or datasets.load_dataset. Useful for modeling when weeds emerge relative to crop sowing, thermal time and photoperiod effects, and cross-site comparison of weed biology. Distributed by OPheno under CC BY 4.0; credit the dataset and its listed contributors.

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/OPheno/Weed-phenology/train.csv")
df.head()
```

## Data structure

File types in sampled files: PNG, CSV

Example file: `train.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/b3ad0fa6-1293-5499-9b8d-cd0d8c977d40
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/b3ad0fa6-1293-5499-9b8d-cd0d8c977d40
- Over MCP: `get_schema_card` with id `b3ad0fa6-1293-5499-9b8d-cd0d8c977d40` at https://api.scigantic.com/mcp

## Related topics

- [CSV datasets](https://scigantic.com/topics/csv)
- [PNG datasets](https://scigantic.com/topics/png)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
