# MH-Weed16: Indian Soybean Field Weed Images with 62,052 Bounding Boxes across 16 Weed Species, Maharashtra (COEP Technological University, AgML Mirror)

## Facts

- Provider: Sayali Shinde and Vahida Attar (COEP Technological University Pune; IDEAS Technology Innovation Hub, Indian Statistical Institute Kolkata); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/d3n3mgjjbv?version=2)
- Size: 8 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/MH_Weed16_weed_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/d3n3mgjjbv.2
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/MH_Weed16_weed_detection
- Page: https://scigantic.com/archive/d941bd35-2e3e-50ea-97be-4f65a80c991f
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

MH-Weed16 was collected in soybean fields in Maharashtra, India, between July and November 2023 under varied natural field conditions, with annotation guided by agricultural experts. The full release holds 18,677 images of 16 weed species plus 7,577 crop samples; crop and weed interactions were photographed top-down so that weed area can be estimated from the boxes, and 282 UAV images add an aerial view. This mirror holds the 6,656 box-annotated weed images with 62,052 bounding boxes across 15 categories. Useful for weed species detection and crop and weed discrimination in Indian soybean farming, and for selective weeding and targeted herbicide application. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/MH_Weed16_weed_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 Sayali Shinde and Vahida Attar et al. and the DOI 10.17632/d3n3mgjjbv.2.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/MH_Weed16_weed_detection")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00006.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/d941bd35-2e3e-50ea-97be-4f65a80c991f
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/d941bd35-2e3e-50ea-97be-4f65a80c991f
- Over MCP: `get_schema_card` with id `d941bd35-2e3e-50ea-97be-4f65a80c991f` 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)
