New Winetech funded project 2018 - This project’s objective is to allow researchers to develop a remote sensing - machine learning framework for rapid, cost-effective, real-time monitoring of vineyard performance. The framework could form the basis for further development and extend the utility of the framework that could then be employed in a myriad of applications. These include yield estimation, fruit quality assessment, stress (pests and disease, drought, etc.) detection, and monitoring nutrient status.
This study aims to generate models for vineyard performance monitoring using terrestrial LiDAR and terrestrial hyperspectral imaging. Models will be created using advanced machine learning techniques and will be tested across cultivars to assess their operational potential. Additionally, the utility of combining terrestrial LiDAR and terrestrial hyperspectral imaging will be evaluated as a means to improve the assessment of vineyard performance. It is envisaged that a combination of the two technologies will provide an enhanced data product for extracting valuable information regarding vineyard performance.
A key output of the research is the identification of specific spectral bands that could be used to monitor and evaluate vineyard performance, specifically water stress. These spectral bands will ultimately be used to inform the design of a customised multispectral sensor with the potential to outperform traditional indices such as NDVI. A customised multispectral sensor will be more cost-effective to produce, easier to use, and be employed for a myriad of applications within precision viticulture.
Researcher: NK Poona