# Deoxynivalenol (DON) Mycotoxin in Wheat by Near-Infrared (NIR) Spectroscopy: 408 Samples from Austria and France (Food AI Nexus Curation)

## Facts

- Provider: Nadeak, Anlanger, Rennhofer, Sulyok and Freitag (BOKU University); Food AI Nexus curation
- License: CC-BY-4.0 (https://zenodo.org/records/20931697)
- Size: 10 files
- Format: CSV, Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/food-ai-nexus/wheat-deoxynivalenol-nir-austria-france
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.20931697
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/food-ai-nexus/wheat-deoxynivalenol-nir-austria-france
- Page: https://scigantic.com/archive/ccbf77b9-7cad-54a9-a457-33e18a232329
- Keywords: Agriculture & Environment, spectroscopy, CSV, Parquet, Hugging Face

## About

Near-infrared spectra of wheat naturally contaminated with the Fusarium mycotoxin deoxynivalenol (DON, vomitoxin), deposited on Zenodo by Nadeak, Anlanger, Rennhofer, Sulyok and Freitag (BOKU University, Austria). The 408 physical samples, 291 Austrian harvests from 2019 to 2024 and 117 French from 2021, were each scanned twice on a Foss DS2500 Vis-NIR benchtop spectrometer, as intact kernels and after milling, giving 816 spectra of 4,200 points from 400 to 2499.5 nm at 0.5 nm steps. Reference DON and total DON concentrations come from an LC-MS/MS multi-mycotoxin method. The curated release has two Parquet tables in data/ (intact and milled, same samples and labels), the original Excel workbooks byte for byte in source/ with checksums, and a script that rebuilds the tables. Supports chemometrics and machine learning for rapid mycotoxin screening: classifying grain against the EU maximum level of 1000 µg/kg DON or regressing concentration from the spectrum. Load with datasets.load_dataset or pandas. Source dataset DOI 10.5281/zenodo.20931697, licensed CC BY 4.0 by the authors; cite Nadeak et al. (2026), ChemRxiv doi:10.26434/chemrxiv.15006267/v1.

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/food-ai-nexus/wheat-deoxynivalenol-nir-austria-france/column_map.csv")
df.head()
```

## Data structure

File types in sampled files: CSV, Parquet

Example file: `column_map.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ccbf77b9-7cad-54a9-a457-33e18a232329
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ccbf77b9-7cad-54a9-a457-33e18a232329
- Over MCP: `get_schema_card` with id `ccbf77b9-7cad-54a9-a457-33e18a232329` at https://api.scigantic.com/mcp

## Related topics

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