Evaluation of Visible-Near Infrared Reflectance Spectra of Avocado Leaves as a Non-destructive Sensing Tool for Detection of Laurel Wilt

Abstract

Laurel wilt, caused by the fungus Raffaelea lauricola, affects the growth, development, and productivity of avocado, Persea americana. This study evaluated the potential of visible-near infrared spectroscopy for non-destructive sensing of this disease. The symptoms of laurel wilt are visually similar to those caused by freeze damage (leaf necrosis). In this work, we performed classification studies with visible-near infrared spectra of asymptomatic and symptomatic leaves from infected plants, as well as leaves from freeze-damaged and healthy plants, both of which were non-infected. The principal component scores computed from principal component analysis were used as input features in four classifiers: linear discriminant analysis, quadratic discriminant analysis (QDA), Naïve-Bayes classifier, and bagged decision trees (BDT). Among the classifiers, QDA and BDT resulted in classification accuracies of higher than 94% when classifying asymptomatic leaves from infected plants. All of the classifiers were able to discriminate symptomatic-infected leaves from freeze-damaged leaves. However, the false negatives mainly resulted from asymptomatic-infected leaves being classified as healthy. Analyses of average vegetation indices of freeze-damaged, healthy (non-infected), asymptomatic-infected, and symptomatic-infected leaves indicated that the normalized difference vegetation index and the simple ratio index were statistically different.

Fusion of sensor data for the detection and differentiation of plant diseases in cucumber

“…Different non‐invasive and optical sensors have been shown to have the capability to detect plant diseases at different stages of disease development (Chaerle & Van Der Straeten, ; Naidu et al ., ; Mahlein et al ., ; Sankaran et al ., ). However, to establish sensor applications for practical use in the field or greenhouse, the impact of plant diseases on plant physiology and on the optical properties of plants has to be assessed, because plant–pathogen interactions are highly specific.…”

“…However, as mentioned recently by Sankaran et al . (), the classification method and the accuracy depend strongly on the type of data and their application.…”

Laurel Wilt in Natural and Agricultural Ecosystems: Understanding the Drivers and Scales of Complex Pathosystems

“…Visible-near infrared spectroscopy has been tested for the nondestructive detection of laurel wilt on avocado [190]. Classification studies were conducted with visible near infrared spectra of asymptomatic and symptomatic leaves from plants artificially infected with R. lauricola, as well as leaves from noninfected freeze-damaged and healthy plants.…”

Evaluation of repellents for the redbay ambrosia beetle, Xyleborus glabratus, vector of the laurel wilt pathogen

“…For avocado, pre‐symptomatic aerial detection of laurel wilt diseased plants using spectral imagery is in development (Sankaran et al. ; de Castro et al. ), but not yet operational.…”

“…Entomopathogenic fungi have been described that infect X. glabratus, but they kill the beetles after they bore into the wood, not preventing the inoculation with R. lauricola . For avocado, pre-symptomatic aerial detection of laurel wilt diseased plants using spectral imagery is in development (Sankaran et al 2012;de Castro et al 2015), but not yet operational. Overall, there is no reliable tool available to prevent R. lauricola infection; consequently, there is a crucial need for management tools to prevent X. glabratus attack and to slow the spread of laurel wilt disease.…”