Breakthrough in whisky analysis: Artificial intelligence distinguishes between American and Scotch whiskies with high accuracy, predicting notes and origin from molecular constituents.
AI Distinguishes Between Aromas of US and Scottish Whiskies with High Accuracy
The development of artificial intelligence (AI) has led to a significant breakthrough in the field of whisky analysis. Researchers have successfully used AI algorithms to predict the notes that waft off whisky and determine whether it was made in the US or Scotland.
A team of experts, led by Dr Andreas Grasskamp at the Fraunhofer Institute for Process Engineering and Packaging in Freising, Germany, obtained the chemical makeup of 16 US whiskeys and Scottish whiskies. They then used this information to train AI algorithms to predict the five major aromas and origin of the drinks from their molecular constituents.
The results were impressive, with one algorithm identifying the five strongest notes in each whisky more accurately than any individual on an expert panel. This achievement is a significant step towards automated systems that can predict the complex aroma of whisky from its molecular makeup.
The researchers found that certain compounds, such as menthol and citronellol, helped to identify US whiskeys, which often have a caramel-like note. On the other hand, methyl decanoate and heptanoic acid were important for identifying scotch, which often has a smoky or medicinal aroma.
The use of AI in whisky analysis has several potential applications beyond predicting the notes that waft off a dram. For instance, it can be used to detect counterfeit products through discrepancies in their smell, or to find the best ways to blend old recycled plastics into new products without the smell being noticeable.
Dr William Peveler, a senior lecturer in chemistry at the University of Glasgow, noted that while the study involved only a small number of whiskies, it has the potential to provide more “stability” than a human taste panel. He added that further research is needed to understand how AI would perform when faced with a larger variety of whiskies and how it would deal with flavor notes that develop over time.
The study’s findings have been published in Communications Chemistry, highlighting the growing importance of AI in various fields, including chemistry and whisky analysis.