We've updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.


AI Can Tell a Wine’s Vineyard With 100% Accuracy

Red wine glass in front of vineyard.
Credit: Kym Elli/Unsplash
Listen with
Register for free to listen to this article
Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

Read time: 2 minutes

AI may have just replaced another profession: wine tasters.

By applying machine learning tools to chemical data, researchers say they have succeeded in identifying, “with 100% accuracy”, the molecular signature of red wines from seven major estates in the Bordeaux region.

The team from the University of Geneva (UNIGE) and the Institute of Vine and Wine Science at the University of Bordeaux  say their method, published in Communications Chemistry, could pave the way for new tools to combat wine counterfeits.

AI like a fine wine

It’s long been said by sommeliers that each wine has a taste unique to its own vineyard and the soil it was grown in. Now it seems AI agrees.

Researchers used gas chromatography-mass spectrometry to analyze the chemical makeup of 80 red wines harvested from 7 estates in Bordeaux between 1990 and 2007. They then processed those data with machine learning, a field of AI in which algorithms learn to identify recurring patterns in sets of information.

“Instead of extracting specific peaks and deducing concentrations, this method allowed us to take into account each wine’s complete chromatograms – which can comprise up to 30,000 points –including ‘background noise’, and to summarize each chromatogram into two X and Y coordinates, after eliminating unnecessary variables,” said Michael Schartner, a former postdoctoral scholar in the Faculty of Medicine at UNIGE and first author of the study. “This process is called dimensionality reduction.”

By placing the new coordinates on a graph, the researchers were able to see seven “clouds” of data points. They found that each of these clouds grouped together vintages from the same Bordeaux estate on the basis of their chemical crossover.

“This allowed us to show that each estate does have its own chemical signature,” said Stéphanie Marchand, a professor at the Institute of Vine and Wine Science at the University of Bordeaux and co-author of the study. “We also observed that three wines were grouped together on the right and four on the left, which corresponds to the two banks of the Garonne on which these estates are located.”

This clumping of data, though defined, was relatively broad, revealing that the chemical identity of the wines was drawn from a chemical spectrum.

“Our results show that it is possible to identify the geographical origin of a wine with 100% accuracy, by applying dimensionality reduction techniques to gas chromatograms,” said Alexandre Pouget, a professor of neuroscience at the University of Geneva and co-author of the paper.

Pouget and his colleagues say their work paves the way for the development of tools to help combat wine counterfeiting more effectively.

Reference: Schartner M, Beck JM, Laboyrie, J. Riquier L, Marchand S, Pouget A. Predicting Bordeaux red wine origins and vintages from raw gas chromatograms. Commun. Chem. 2023. doi:10.1038/s42004-023-01051-9


This article is a rework of a press release issued by the University of Geneva. Material has been edited for length and content.