Better beer: are computers the way forward?
Beer might have an even tastier future say Belgian researchers, who used a machine learning method to make better tasting beers. Their research is reported in Nature Communications.
Kevin Verstrepen and colleagues characterised over 200 chemical properties from 250 Belgian commercial beers across 22 beer styles, such as Blond and Tripel beers. They linked these to descriptive sensory profiling data from a trained tasting panel of 16 people and data from more than 180,000 public consumer reviews from an online beer review database called RateBeer. With this large dataset, the authors trained machine learning models to correlate and predict flavour and consumer appreciation from the beers’ chemical profile. They tested the effectiveness of the model by using its predictions to modify an alcoholic and non-alcoholic commercial beer and achieved higher overall appreciation among trained panellists in blind tastings.
Using the computer predictions, the team were able to modify commercial beers — both alcoholic and non-alcoholic — to receive a higher overall rating from trained panellists in blind tastings.
Understanding and predicting whether consumers will enjoy new food flavours is a complex task that is influenced by numerous chemical compounds and external factors. This presents a challenge in deciphering the relationship between beer chemistry and consumer preferences. Typically, this is investigated through consumer trials, which can be limited and somewhat inefficient.
ROKLive 2025 program released
Rockwell Automation has unveiled its program for ROKLive 2025 on the Gold Coast from 29–31...
Wine and grape sector review report has 14 recommendations
Wine Australia has released Dr Craig Emerson's independent analysis of the grape and wine...
Australia free from bird flu in poultry
The Victorian response to an outbreak of H7 high pathogenicity avian influenza (HPAI) in poultry...