Using digital technology to detect grape quality

By Rachel Arthur

- Last updated on GMT

Hyperspectral camera and lighting system
Hyperspectral camera and lighting system

Related tags Wine

Researchers at the Australian Wine Research Institute (AWRI) are trialling a new way to measure bunch rot and non-grape matter by using near infrared hyperspectral imaging at the weighbridge.

Such technology is already used widely in the food industry to test for disease or other parameters such as moisture or protein levels in wheat. The project hopes to take this technology into a wine setting so that winemakers can accurately assess fruit for bunch rot and matter other than grapes (MOG).

The technology depends on the specific spectral signature found in all organic products.

AWRI senior research scientist Dr Bob Dambergs explained large wineries need to be able to accurately assess fruit when it comes over the weighbridge.

“You might have inspected the vineyard three to four days before, but in conditions like we had last vintage – when botrytis spread rapidly – things could have changed dramatically.”

Fingerprinting

The first stage of the work has been carried out in the lab, using infected grapes, to identify the ‘fingerprints’ that winemakers want to look out for, allowing for quicker testing.

“The initial work we’ve done is with full spectral scans and we know that we can pick up infected fruit with that wavelength range, but with those scans we can also start narrowing it down to certain wavelengths so we can make a system that’s cheaper and faster and needs less data storage capacity,”​ continued Dambergs.

The next stage will be to take the technology to a weighbridge or simulated setting, to test the logistical aspects of the technology.

“We need to get a better understanding of the opportunities and the restrictions of sampling on site,”​ said Dr Paul Petri, who is also working on the project. "Would it be feasible to have a camera mounted over the bin to take the image or are there going to be issues with how far the camera is from the bin? Is the resolution high enough and can we get the right lighting to get the spectral signature that we need?”

Related topics R&D

Related news