# Hawaii Ground Beetles: NEON PUUM Carabid Specimen Images with Elytra and Pronotum Measurements

## Facts

- Provider: Imageomics Institute and AI and Biodiversity Change Global Center (Rayeed, Khurana, East et al.); specimens from NEON
- License: CC-BY-4.0 (https://huggingface.co/datasets/imageomics/Hawaii-beetles)
- Size: 2,040 files
- Format: PNG, CSV (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/imageomics/Hawaii-beetles
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://github.com/Imageomics/carabidae_beetle_processing
- Page: https://scigantic.com/archive/4eb2c54c-1a2e-57d7-9c56-ac1906da0478
- Keywords: Environmental Science, image segmentation, PNG, CSV, Hugging Face

## About

High-resolution images of ground beetles (Coleoptera: Carabidae) collected in pitfall traps by the U.S. National Ecological Observatory Network (NEON) at the Pu'u Maka'ala Natural Area Reserve (PUUM) on the Island of Hawai'i between 2018 and 2024, photographed in 2025 with a Canon EOS 7D during the Imageomics Institute and ABC Global Center Experiential Introduction to AI and Ecology course. The release has 1,614 PNG images of individual specimens from 14 species (for example Mecyclothorax konanus), segmented from tray-level group images that are also included. images_metadata.csv links each specimen to its NEON individualID, taxonID, scientific name, plot, trap direction, collection date and NEON catalog number (DP1.10022.001); trait_annotations.csv gives scalebar, maximum elytral length, maximum elytral width and basal pronotum width as pixel coordinates and calibrated centimeters. Uses include species classification, instance segmentation of natural-history trays, automated morphometric trait extraction and linking traits to NEON environmental data. Images and metadata are licensed CC BY 4.0; cite Rayeed et al., 'A continental-scale dataset of ground beetles with high-resolution images and validated morphological trait measurements' (arXiv 2601.10687).

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/imageomics/Hawaii-beetles/group_images/metadata.csv")
df.head()
```

## Data structure

File types in sampled files: PNG, CSV

Example file: `group_images/metadata.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/4eb2c54c-1a2e-57d7-9c56-ac1906da0478
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/4eb2c54c-1a2e-57d7-9c56-ac1906da0478
- Over MCP: `get_schema_card` with id `4eb2c54c-1a2e-57d7-9c56-ac1906da0478` at https://api.scigantic.com/mcp

## Related topics

- [CSV datasets](https://scigantic.com/topics/csv)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
- [PNG datasets](https://scigantic.com/topics/png)
