Rapid estimation of DON content in wheat flour using close‐range hyperspectral imaging and machine learning

Abstract

Fusarium head blight (FHB) is one of the most destructive fungal diseases affecting wheat (Triticum aestivum). Moreover, it is notorious for producing mycotoxin deoxynivalenol (DON), posing a significant global threat to food and feed safety. Traditional methods like enzyme‐linked immunosorbent assay (ELISA) and gas chromatography‐mass spectrometry (GC‐MS) are commonly used to assess DON levels in grain or flour samples and are time‐consuming and expensive. Therefore, a faster, cost‐effective method to estimate DON content is needed, especially for enhancing breeding efforts to reduce DON levels in wheat. In this study, we envisioned integrating close‐range hyperspectral imaging with deep learning (DL) models to estimate DON content in wheat meal/flour. We selected 243 advanced breeding lines from the South Dakota State University (SDSU) wheat breeding program that were evaluated in FHB nurseries (2019–2020 and 2020–2021). The wheat meal samples were analyzed for DON content using GC‐MS and subsequently subjected to close‐range hyperspectral imaging. We evaluated three conventional machine learning (ML), two DL models and data augmentation. Among the conventional ML models, partial least squares regression (PLSR) (with R2P = 0.88 and 0.90 for original and augmented datasets, respectively) demonstrated the highest prediction accuracies for DON content. However, the one‐dimensional convolutional neural network (1D‐CNN) achieved the highest prediction accuracies (R2P = 0.90 and = 0.96 for original and augmented datasets, respectively) compared to all tested models and demonstrated the lowest error. In conclusion, integration of advanced hyperspectral imaging with ML approaches exhibits significant potential for high‐throughput and cost‐effective estimation of DON content in wheat, thereby accelerating wheat breeding efforts for reduced DON levels.