Only in Australia. Researchers from the University of Melbourne have developed a cheap, portable ‘electronic-nose’, or ‘e-nose’, that uses machine learning to quickly assess beer quality based on its aroma.
Why? With Aussies’ love of craft beer ever-growing, brewers are increasingly experimenting with different flavour profiles to attract demanding drinkers (beer snobs).
But in smaller breweries – particularly those that don’t use pasteurisation – beers can develop off-flavours or aromas and these are not always picked up by the master brewer and their offsiders – because taste is highly subjective.
The e-nose (pictured inset) – which looks like a small microchip – is designed to get around this.
Placed face-down over a sample of beer in a beaker so the sensors can measure the various gases above the beer, the device has proved to be simple to use – and has 97% accuracy
The team did test their findings with a traditional ‘sensory’ (beer-sniffing) session by 12 trained panelists (drinkers) who assessed the intensity of different beer aromas – hops, spicy, floral, fruity, burnt sugar, grains, yeast, nut and carbonation mouthfeel – but the e-nose still came out on top.
The technology isn’t just good for sniffing out a ‘bad’ beer either. The researchers say the device also has the potential to assess other food and beverages at all stages of production and has already been tested to detect smoke taint in wine.
So, will the e-nose replace a master brewer’s taste?
Absolutely not, says Associate Professor Fuentes. “I find that brewers are not against technology. They embrace it.”
We’ll drink to that.
