{"id":217203,"date":"2024-03-26T17:51:20","date_gmt":"2024-03-26T17:51:20","guid":{"rendered":"https:\/\/michigandigitalnews.com\/index.php\/2024\/03\/26\/flavour-predicting-ai-can-tell-brewers-how-to-make-beer-taste-better\/"},"modified":"2025-06-25T17:19:54","modified_gmt":"2025-06-25T17:19:54","slug":"flavour-predicting-ai-can-tell-brewers-how-to-make-beer-taste-better","status":"publish","type":"post","link":"https:\/\/michigandigitalnews.com\/index.php\/2024\/03\/26\/flavour-predicting-ai-can-tell-brewers-how-to-make-beer-taste-better\/","title":{"rendered":"Flavour-predicting AI can tell brewers how to make beer taste better"},"content":{"rendered":"

[ad_1]
\n<\/p>\n

\n
\n
\"\"<\/div>
\n
\n

Beer brewers generate a huge variety of flavours from just a handful of ingredients<\/p>\n

Kutredrig\/Getty Images<\/p>\n<\/div>\n<\/figcaption><\/figure>\n<\/p>\n

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.<\/p>\n

Predicting flavour from chemical compounds<\/a> 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.<\/p>\n

To address this, Kevin Verstrepen<\/a> at KU Leuven in Belgium and his colleagues have developed an AI model that can predict flavour profiles based on a beer\u2019s chemical components and make suggestions for how to improve the flavour.<\/p>\n

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.<\/p>\n

\u201cThese 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,\u201d says Verstrepen. \u201cThe fact that now, with machine learning, you can actually accurately predict this is quite amazing.\u201d<\/p>\n

<\/p>\n

Verstrepen and his team used the model to predict how to improve the flavour of a beer by adding a mixture of certain compounds, such as lactic acid and ethyl acetate. The resulting beer was given a significantly higher rating by the panel of trained tasters.<\/p>\n

In separate work that has yet to be published, non-alcoholic beers became indistinguishable from regular beer after making changes suggested by the model, says Verstrepen.<\/p>\n

The idea is that brewers should aim to implement the AI\u2019s recommendations by tweaking their recipes, rather than simply adding flavours, he says. \u201cIn beer brewing, it\u2019s not really acceptable to just add pure aroma compounds. It\u2019s just malt, hops, water and yeast that have to do the trick.\u201d<\/p>\n

\u201cSo, I really see it as a tool. It will be used especially to make better alcohol-free beer, but it\u2019s not taking away the art of making good beer in an artisanal way,\u201d says Verstrepen.<\/p>\n

\n

Topics:<\/p>\n