Upgrade for breweries

Artificial intelligence makes beer tastier

Are breweries facing a digital revolution?(Bild: LIGHTFIELD STUDIOS - stock.adobe.com)

With the help of artificial intelligence, researchers want to create new beers that delight consumers. Beers modified with AI are already receiving better overall ratings.

The team from Belgium, who published their findings in the journal "Nature Communications", explain that until now it has only been possible to find out which alcoholic and non-alcoholic flavors are well received by the market through consumer tests to a limited extent.

The new method could help food manufacturers to meet specific consumer demands more efficiently and cost-effectively.

It is generally complex to predict which new food flavors consumers will like, explain the researchers led by Kevin Verstrepen from the Catholic University of Leuven. This is mainly due to the fact that there are an immense number of flavor-active chemicals in food.

There are also interactions and complex enhancing or diminishing effects on taste perception. Sweetness and bitterness, for example, mask each other.

200 chemical properties recorded

The scientists have now recorded over 200 chemical properties of 250 Belgian beers belonging to 22 different beer styles such as blonde, tripel and lager. These were combined with descriptive sensory profile data from a trained tasting panel of 16 people on hop, malt and yeast aromas, off-flavors and spices, for example, as well as data from more than 180,000 consumer reviews from an online beer review database.

The use of trained tasters is common, but this incurs high costs. Online rating databases, on the other hand, are prone to errors because they also reflect factors such as price or the current cult status of a product.

Overall, the models used are still immature, the research team concludes. More comprehensive data sets are crucial for further improvements. In addition, it must be clear that the models can only recognize correlations, but not causal relationships. It is also emphasized that AI approaches should not lead to an increase in the dependency potential of alcoholic beverages.