AI used to identify Bordeaux wines

A team from the University of Geneva in Switzerland has used AI to assess where seven wines from Bordeaux originated from. They are able to identify the winery that the wines came form with 100% accuracy.

The test involved analysing 73 wines using Gas chromatography to find individual compounds. The plan was to create a unique fingerprint for Bordeaux estates ranging from 1990 to 2007. An AI was then trained to look at the results of the Gas chromatography, a further 7 wines were then used to test the accuracy of the AI at predicting which estates the wines came from. The results were 100% accurate.

The goal was to identify a specific, invariable chemical signature for each estate. Co-author Stéphanie Marchand, a professor at the Institute of Vine and Wine Science at the University of Bordeaux, said ‘This allowed us to show that each estate does have its own chemical signature. 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.’

While the program traced wines back to the correct châteaux with 99% accuracy, it struggled to distinguish vintages, reaching a 50% accuracy at best.