Skip to main content
Knowledge4Policy
Knowledge for policy
Supporting policy with scientific evidence

We mobilise people and resources to create, curate, make sense of and use knowledge to inform policymaking across Europe.

Harnessing machine learning for grain mycotoxin detection

Global Food and Nutrition Security

Highlights:

  • Comprehensive review of common grain mycotoxins.
  • Non-destructive techniques to detect the grain mycotoxins.
  • Machine learning techniques used to detect grain mycotoxins.
  • Insights into challenges and prospects in machine learning-driven mycotoxin detection.
  • Recommendations to overcome the current challenges for grain mycotoxin and improve crop safety.

Abstract:

Detecting mycotoxins such as deoxynivalenol, aflatoxins, and zearalenone in grains is crucial for ensuring crop safety and maintaining consumer health, both for humans and animals. These toxins pose serious health risks, affect the marketability of grains in international markets, and influence their economic value. Hence, this paper reviews the use of machine learning (ML) in detecting and managing grain mycotoxins to transform grain safety measures. The review will cover the common mycotoxins in grains, their adverse effects, and techniques for detecting mycotoxin data. It describes the latest ML models for detecting or predicting these toxins. The paper evaluates the effectiveness of these ML techniques, identifies research gaps, and suggests potential solutions. Overall, this review establishes a comprehensive baseline for future research on grain mycotoxin detection, assessing the extent to which various ML methodologies have been explored. This paper aims to create a foundational understanding for readers about the state-of-the-art techniques in ML. This area will further advance readers' knowledge of detecting and managing mycotoxins in grains.