beer In Belgium it’s more than a tradition, it’s almost part of a religion, where everyone in the country must make a pilgrimage to bars to drink this popular concoction at some point during the day. And although it is classified as one of the best in the world, there is still a group of scientists who want to improve it further with the help of AI.
This is achieved by fine-tuning machine learning programs to filter characteristics that improve smells and tastes.
Professor Kevin Verstrepen from the University of Leuven, who led the study, said AI could help unravel the complex relationships involved in human odor perception.
“Beer, like most foods, contains hundreds of different flavor molecules that are detected by our tongue and nose, and our brain integrates them into a single image. However, the compounds interact with each other, so how we perceive one also depends on the concentration of the others,” he said.
In a paper in the journal Nature Communications, Verstrepen and his colleagues report how they analyzed the chemical composition of 250 Belgian commercial beers in 22 different styles, including lagers, fruit beers, lagers, West Flanders beers and non-alcoholic beers.
Properties studied include alcohol strength, pH, sugar concentration, and the presence and concentration of more than 200 different flavor compounds, such as esters produced by yeast and hop terpenoids, which are involved in creating fruity notes.
“Small changes in the concentration of chemicals can have a big impact, especially when multiple components start to change,” Verstrepen said, adding that one surprise was that some substances traditionally known as “switches” can be positive if they are present in lower concentrations and occur in combination. with other aromatic compounds.
Using various data sets, the team built models using machine learning—a form of artificial intelligence—to predict the taste of beer and rate it based on its composition.
They then used the results to improve existing commercial beers, essentially adding substances flagged by the models as important predictors of the overall score, such as lactic acid and glycerol.
“AI models predict chemical changes that could optimize beer, but brewers still have to achieve this based on the recipe and brewing methods,” Verstrepen concluded.
Source: Digital Trends
I am Garth Carter and I work at Gadget Onus. I have specialized in writing for the Hot News section, focusing on topics that are trending and highly relevant to readers. My passion is to present news stories accurately, in an engaging manner that captures the attention of my audience.
