Honey fraud is a significant issue for the food industry. What is honey fraud? Typically, it involves mislabeling where honey was produced or what types of flowers the bees collected nectar from. Honey made from a single type of flower is often more expensive because of the unique flavor it provides or from potential health benefits. Sometimes even cheap alternatives like sugar syrups are labelled as honey. It turns out that honey is one of the most fraud-prone commodities in global trade, with fraud estimated to occur in up to 10% of the honey traded internationally. Honey from some countries, such as China and India, has had 30% or more of samples found to be fraudulent.
Researchers at McGill University in Montreal have developed an AI-powered method to verify the origin of honey thereby ensuring that what is on the label corresponds to what is in the jar.
The McGill method can determine what kind of flowers the bees visited to produce a particular sample of honey. Previous honey authentication involved pollen analysis, which is ineffective for honey that was processed or filtered. The new method uses high-resolution mass spectrometry which captures a unique chemical “fingerprint” from the honey. Machine learning algorithms read the fingerprint to identify the honey’s origin.
The researchers tested their methodology on a variety of honey samples which they then compared with honey from known botanical sources. Using previous methods for honey authentication can take days. The McGill method takes only minutes and works regardless of how the honey was processed.
According to the researchers, people deserve to know that the honey they buy is what it claims to be, and honest honey producers deserve protection from fraudulent competitors.
**********
Web Links
Fighting honey fraud with AI technology
Photo, posted May 6, 2012, courtesy of Emma Jane via Flickr.
Earth Wise is a production of WAMC Northeast Public Radio