News

Smart grape: AI project to determine grape quality and ripeness could help in climate change battle

10 August 2021 By Arabella Mileham

A German research institute has launched a project using artificial intelligence (AI) to determine grape quality and ripeness that it says could also eventually be used in the battle against climate change.

The Smart Grape project by the Fraunhofer Institute for Process Engineering and Packaging IVV is using infrared spectroscopy and AI to analysise grapes, and work out if they are .

Infrared spectroscopy is a non-destructive optical technique which uses infrared radiation to provide information about the chemical composition of a particular sample. The institure says that this makes it an idea medium to use to work out if the grapes meet the required parameters for a great wine. It is also using mid-infrared wavelenghts (of between 2500 and 50,000 nm to characterize the quality of grapes, rather than the near-infrared wavelengths ( between 780 and 2500 nm) that are more commonly used. This is likely to provide large amounts of information, it said.

“The aim of the SmartGrape joint project is to develop a compact measuring system for the rapid, non-destructive determination of grape quality on the basis of infrared spectroscopy in the mid-infrared (MIR) range,” the institute said, noting that “the information content in the mid-infrared range is significantly higher than near-infrared, which means that more precise information can be provided.”

Once all the data and chemical analysis has been generated by the infrared spectroscopy it is transfered to data sets which are evaluated by AI.

The benefit, the institute says is that AI is able to take into account non-linear correlations and interaction effects which would take far longer to process using more conventional methods. It will also enable the system to be accessed across several organisations and provide a tool for greater digitalization in viticulture.

“The system will allow raw materials to be characterized and digitalized simultaneously in a single, direct process — a possibility not offered by conventional methods,” the institute said.

Digitalizing the data will also make it possible to use the data for broader uses – for example the data can be used within the a digital ecosystem developed by the German Federal Ministry for Economic Affairs and Energy (BMWi), which could help share information between different stakeholders throughout the entire production and value chain, from agriculturalists, machinery to research institutions. This could help with the battle to conserve resources and boost efficiency within the agricultural sector in response to climate change for example

“Examples include the possibility of recording changes in quality over many harvest years or the correlation of external influencing factors (e.g., climate, soil quality) and their impact on the composition of the grapes and, ultimately, on the quality of the wine,” the institute said.

The project is funded by the German Federal Office for Agriculture and Food (BLE) and the German Federal Ministry of Food and Agriculture (BMEL) and being conducted in collaboration with IRPC Infrared-Process Control GmbH, LiquoSystems GmbH, QuoData GmbH and the Weincampus Neustadt.

EU wine reforms aim to tackle oversupply and climate change

Is Monastrell the climate-adaptable grape the industry needs?