Imagine for farmers and food inspectors to have a cheap and fast method to determine right away whether agricultural products are contaminated by pesticides. This has come closer to reality through a project initiated by a grant from KENET, the research and education network (NREN) of Kenya.
Today, screening food products for pesticide contamination is a lengthy and costly endeavor, involving careful extraction of samples which are sent to laboratories for analysis in advanced equipment. A research group led by Dr. Ian Kaniu, Senior Lecturer at University of Nairobi, has developed a novel method whereby products can be screened on-site yielding immediate results and without applying physical damage to the product.
The project was initiated in 2022, when Dr. Kaniu was awarded the Research and Innovation Grant by KENET in the Special Interest Group for Computational Modelling and Materials Science.
Detects molecular “fingerprints”
Pesticide residues in food pose significant health risks, particularly in developing countries where regulatory enforcement may be weak. Further, the lack of accessible screening tools has resulted in poor regulatory compliance and undetected exposure.
In Kenya, recent studies have linked prolonged exposure to chlorothalonil with increased risks of cancer, endocrine disruption, and organ toxicity. Chlorothalonil is a widely used pesticide to control fungal diseases in crops.
While traditional screening techniques such as gas chromatography and mass spectroscopy require complex sample preparation and specialized lab infrastructure, the research group has developed a method to detect chlorothalonil in vegetables and other farm produce by diffuse reflectance spectroscopy (DRS). This is an optical technique, which detects molecular signatures from the way light is reflected from the surface of the product.
Machine learning enhances accuracy
When light interacts with pesticide-contaminated produce, a distinct spectral pattern is formed. This is not the end of the story, however, as interpretation of the results can be challenging due to overlapping signals from different substances in the product. Therefore, Dr. Kaniu’s team has applied machine learning algorithms. Here, datasets with spectral information from both pesticide-contaminated and pesticide-free samples are utilized to train the software. As a result, the models can distinguish between contaminated and safe produce. Currently, the precision rates exceed 95%.
With results available in just minutes, DRS ensures that pesticides can be detected quickly, even in the field. This can be a powerful tool for farmers, food safety inspectors, and regulatory bodies.
“The integration of DRS and machine learning to detect pesticide residues is a breakthrough in food safety technology. This innovative approach offers a quick, accurate, and affordable way to screen for chlorothalonil residues, and it has the potential to completely change the way we monitor pesticides in agriculture,” according to KENET’s website.
Looking ahead, the team hopes to apply the method to more pesticides besides chlorothalonil, and to miniaturize detection devices, making handheld and smartphone-integrated sensors more accessible for on-the-spot testing.
The text is inspired by the article “Bridging tech and agriculture: KENET-backed project aims for rapid pesticide testing” at the KENET website.
Contributor
