In-field screening tool for differential harvest of fruit and respective winemaking
Bush fires are becoming more frequent, severe and extensive due to changing climate and intentional fires. When bush fires happen to be close to vineyards, especially around veraison, smoke contamination of grapevines and grapes can occur, which is passed to the winemaking process producing smoke-taint in wines. At the moment, detection of contaminated leaves, canopies and fruit can be achieved with tedious and expensive laboratory analysis.
This research proposed a non-invasive detection system for smoke contaminants in leaves, canopies and berries using remote sensing techniques through proximal (for leaves and berries) and unmanned aerial vehicles (UAV) for canopies. Data analysis and model construction will be performed using machine learning algorithms.
This project follows on from our Digital Vineyard project. Experiments will be conducted in Parkville, The University of Melbourne’s Systems Gardens for proximal smoke detection using NIR on Shiraz leaves. Experiments using proximal NIR and UAV based multispectral and infrared thermal remote sensing will be performed at The Waite Campus from The University of Adelaide. The latter experiment will leverage an existing smoke taint experiment performed in a grapevine cultivar collection.
The same experiment will be conducted using UAV at The North-West University of Agriculture and Forestry for a single cultivar artificially smoked. Preliminary data obtained from seven grapevine cultivars using Near Infrared spectroscopy (NIR) and machine learning models resulted in models with 89.3% accuracy in the detection of smoked berries compared to only 61.6% accuracy for the model found for half berries. These results are consistent to levels of smoke-taint compounds found in different berry organs with higher concentration in the skin compared to pulp and seeds.
The smoke detection method proposed, and single model developed for seven cultivars, can offer grape growers a quick, affordable, accurate, non-destructive and in-field screening tool that can be used for differential harvest of fruit and respective winemaking.
- Sigfredo Fuentes
Veterinary and Agricultural Sciences/MUAIP
University of Melbourne
- Dr Eden Tongson
Veterinary and Agricultural Sciences
University of Melbourne
- Dr Roberta De Bei
University of Adelaide
- Dr Baofeng Su
North West University of Agriculture and Forestry, China