This paper investigates the use of machine learning techniques on hyperspectral images of pistachios to detect and classify different levels of aflatoxin contamination. Aflatoxins are toxic compounds produced by moulds, posing health risks to consumers. Current detection methods are invasive and contribute to food waste. This paper explores the feasibility of a non-invasive method using hyperspectral imaging and machine learning to classify aflatoxin levels accurately, potentially reducing waste and enhancing food safety. Hyperspectral imaging with machine learning has shown promise in food quality control. The paper evaluates models including Dimensionality Reduction with K-Means Clustering, Residual Networks (ResNets), Variational Autoencoders (VAEs), and Deep Convolutional Generative Adversarial Networks (DCGANs). Using a dataset from Leeds Beckett University with 300 hyperspectral images, covering three aflatoxin levels (160 ppn, and >300 ppn), key wavelengths were identified to indicate contamination presence. Dimensionality Reduction with K-Means achieved 84.38% accuracy, while a ResNet model using the 866.21 nm wavelength reached 96.67%. VAE and DCGAN models, though promising, were constrained by dataset size. The findings highlight the potential for machine learning-based hyperspectral imaging in pistachio quality control, and future research should focus on expanding datasets and refining models for industry application.

Aflatoxin contamination in pistachios, caused by Aspergillus flavus and Aspergillus parasiticus, poses significant risks to food safety and global trade due to its carcinogenic properties. This review examines traditional detection methods such as High-Performance Liquid Chromatography and Enzyme-Linked Immunosorbent Assay. Although these techniques are highly precise, they are costly, destructive, and impractical for smallholder farmers. Emerging nondestructive technologies enable rapid, accurate detection without destroying the sample, particularly when Hyperspectral Imaging (HSI) is combined with machine learning. Regulatory thresholds such as the European Union (EU) 8 µg/kg limit for AFB1 create challenges for producers and exporters, especially since HSI methods often lack the precision required for validated quantitative regression at this level on naturally contaminated pistachio kernels. High implementation costs, limited regulatory guidance, and calibration demands hinder its adoption. Climate change heightens contamination risks, calling for predictive models that integrate HSI with environmental data. To support equitable access, especially for smallholder farmers, reducing costs, standardizing protocols, and enhancing global cooperation are essential. These measures will strengthen food safety and regulatory compliance in pistachio production.