Flavour-predicting AI can tell brewers how to make beer taste better
An AI model trained on chemical and perceptual data on 250 Belgian beers can predict the flavour profile of a brew – and how to make it tastier
By Alex Wilkins
26 March 2024
Beer brewers generate a huge variety of flavours from just a handful of ingredients
Kutredrig/Getty Images
An artificial intelligence that can predict how a beer will taste from its chemical make-up could help create alcohol-free versions that taste just like regular ones.
Predicting flavour from chemical compounds is difficult, as complex interactions between ingredients and the psychology of taste can make for surprisingly different perceptions, even between people sampling the same thing.
Read more
Genetically modified tobacco plant produces cocaine in its leaves
Advertisement
To address this, Kevin Verstrepen at KU Leuven in Belgium and his colleagues have developed an AI model that can predict flavour profiles based on a beer’s chemical components and make suggestions for how to improve the flavour.
The model was trained on beer reviews from a panel of 16 expert tasters, who scored each brew for 50 attributes, as well as 180,000 public ratings from an online beer reviewing website. It compared these subjective descriptions with measurements of 226 chemical compounds in 250 Belgian beers.
“These hundreds of compounds are received by our nose and mouth, but mostly nose, and then processed in our brain to give what we think of as a flavour,” says Verstrepen. “The fact that now, with machine learning, you can actually accurately predict this is quite amazing.”
