Tackling a Global Crop Pandemic - From The Air

If an outbreak of Xylella fastidiosa (Xf) occurred in Australia or elsewhere, methods developed by University of Melbourne researchers could be used to rapidly detect and prevent the spread of the disease.

Aerial image acquired from the University of Melbourne’s Airborne Remote Sensing Facility
during flights carried out in the Victorian Mallee region during summer 2020

In a trial in the Mallee last year, funded by the Australian Department of Agriculture, Water and Environment, Professor Pablo Zarco-Tejada and Dr Tomas Poblete scanned several thousand hectares of healthy almond, citrus and olive trees with varying water and nutrient status levels as baselines to better adapt Xf detection models developed in Europe for the particular varieties and management practices in Australian agriculture.

Their international research project is focused on the early detection of Xf, which is arguably the greatest disease threat to food security and agricultural productivity worldwide but isn’t yet present in Australia.

Published in Nature Communications in October, this research demonstrates that hyperspectral imaging and a novel algorithm can distinguish the disease from water-induced stress and increase Xf detection to up to 92 per cent accuracy while reducing uncertainty to below six per cent across different hosts.

Airborne hyperspectral image acquired by the University of Melbourne’s Airborne Remote Sensing Facility, used to extract the spectral data for disease detection and machine learning algorithms

You can read more about the research in the University of Melbourne’s Pursuit.