Detection of Xylella fastidiosa infection symptoms with airborne multispectral and thermal imagery: Assessing bandset reduction performance from hyperspectral analysis

Poblete, Tomas; Camino, C.; Beck, Pieter S. A.; Hornero, Alberto; Kattenborn, Teja; Saponari, María; Boscia, D.; Navas‐Cortés, Juan A; Zarco‐Tejada, Pablo J.

doi:10.1016/j.isprsjprs.2020.02.010

Cited by 79 publications

(54 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, Gitelson and Merzlyak (1996) showed that traces of chlorophylls a and b and significant content of carotenoids did not change leaf reflectance at 540 nm, suggesting a lesser spectral contribution of carotenoids compared to chlorophylls. The increase in VIS reflectance noted in GTD symptomatic leaves was also reported in other studies that described the hyperspectral behavior of leaves with fungal disease symptoms, like in downy mildew symptomatic grapevine leaves (Calcante et al 2012;Oerke et al 2016), sugar beet leaves with symptoms of Cercospora leaf spot, powdery mildew and sugar beet rust (Mahlein et al 2010), and olive leaves obtained from Xylella fastidiosa infected trees (Poblete et al 2020).…”

Section: Discussionsupporting

confidence: 81%

Leaf hyperspectral reflectance as a potential tool to detect diseases associated with vineyard decline

Junges

Almança

Fajardo

et al. 2020

Trop. plant pathol.

View full text Add to dashboard Cite

Grape production in the Serra Gaúcha region, south of Brazil, is severily constrained by several diseases such as the decline and death syndrome caused grapevine trunk (fungal) diseases (GTDs) and the grapevine leafroll-associated virus (GLRaV). As pathogens induce changes in leaf tissue that modify the reflectance, the spectral signature of asymptomatic and symptomatic grapevine leaves infected by GTDs and GLRaV was analyzed to check whether spectral responses could be useful for disease identification. This work aims at (a) defining the spectral signature of grapevine leaves asymptomatic and symptomatic to GTDs and GLRaV; b) analyzing whether the spectral response of asymptomatic leaves can be distinguished from symptomatic; and (c) defining the most useful wavelengths for discriminating spectral responses. For such, reflectance of leaves in either condition collected in a "Merlot" vineyard during three growing seasons was measured using a spectroradiometer. Principal components and partial least square discriminant analyses confirmed the spectral separation and classes discrimination. The average spectra, difference spectra, and first-order derivative (FOD) spectra indicated differences between asymptomatic and symptomatic leaves in the green peak (520-550 nm), chlorophyll-associated wavelengths (650-670 nm), red edge (700-720 nm), beginning of nearinfrared (800-900 nm), and shortwave infrared. Hyperspectral data was linked to biochemical and physiological changes described for GTD and GLRaV. Variable importance in the projection (VIP) analysis showed that some wavelengths allowed to differentiate the tested pathosystems and could serve as a basis for further validation and disease classification studies.

show abstract

Section: Discussionsupporting

confidence: 81%

Leaf hyperspectral reflectance as a potential tool to detect diseases associated with vineyard decline

Junges

Almança

Fajardo

et al. 2020

Trop. plant pathol.

View full text Add to dashboard Cite

show abstract

“…Unfortunately, at present, there is no cure, and the only solution to stop the epidemic spread of the disease is to pluck infected trees. A disease management strategy would be much more efficient if the asymptomatic or infected plants with visible symptoms of desiccation were identified at an early stage, to reduce the spreading of the pathogen and the risk of infection to neighboring trees [3][4][5]. Disease severity on olive plants can be quantified in several ways (occurrence, intensity, severity level) and at different scales (leaves, stems, fruits, portion/whole plants, or small quadrats).…”

Section: Introductionmentioning

confidence: 99%

Semi-Automatic Method for Early Detection of Xylella fastidiosa in Olive Trees Using UAV Multispectral Imagery and Geostatistical-Discriminant Analysis

et al. 2020

View full text Add to dashboard Cite

Xylella fastidiosa subsp. pauca (Xfp) is one of the most dangerous plant pathogens in the world. Identified in 2013 in olive trees in south–eastern Italy, it is spreading to the Mediterranean countries. The bacterium is transmitted by insects that feed on sap, and causes rapid wilting in olive trees. The paper explores the use of Unmanned Aerial Vehicle (UAV) in combination with a multispectral radiometer for early detection of infection. The study was carried out in three olive groves in the Apulia region (Italy) and involved four drone flights from 2017 to 2019. To classify Xfp severity level in olive trees at an early stage, a combined method of geostatistics and discriminant analysis was implemented. The results of cross-validation for the non-parametric classification method were of overall accuracy = 0.69, mean error rate = 0.31, and for the early detection class of accuracy 0.77 and misclassification probability 0.23. The results are promising and encourage the application of UAV technology for the early detection of Xfp infection.

show abstract

“…Algunos de estos procesos son potencialmente detectables mediante técnicas de teledetección hiperespectral y pueden ser indicadores no específicos del estado fisiológico de salud de los árboles (Carter et al, 2001). Los índices que encontramos como principales para diferenciar árboles sanos de árboles estresados, en concreto el índice de reflectancia fotoquímica (PRI) y los índices calculados para bandas red edge tales como el índice de Vogelmann (VGO1), han mostrado ser útiles para diferenciar hojas sintomáticas de no sintomáticas en investigaciones previas (Poblete et al, 2020). El PRI es un índice sensible al proceso de-epoxidación de las xantofilas, mecanismo que se pone en marcha tras un cierre estomático bajo condiciones de estrés hídrico (Suárez et al, 2008).…”

Section: Discussionunclassified

“…Índices relacionados con el estado hídrico de la vegetación (PRI) e índices relacionados con la actividad fotosintética (VGO1, VGO2) han mostrado ser representativos para una correcta identificación. Estos resultados están en concordancia con los encontrados en Poblete et al (2020) o Calderon et al (2015.…”

Section: Discussionunclassified

“…Actualmente, los sensores hiperespectrales y térmicos de alta resolución aerotransportados pueden detectar en cada árbol cambios fisiológicos, que después son interpretados mediante algoritmos de aprendizaje automático y modelos físicos. Esos indicadores permiten determinar, para cada árbol de la imagen, si está sano o enfermo, independientemente de que en el campo muestre síntomas visuales o no (Beck et al, 2015, Poblete et al, 2020.…”

Section: Introductionunclassified

See 1 more Smart Citation

Uso de imágenes hiperespectrales para la predicción del marchitamiento de Pinus halepensis (Mill.) en el bosque mediterráneo

et al. 2020

View full text Add to dashboard Cite

<p>The increasing negative effects of climate change and the emergence of invasive species in forests around the world require the development of innovative methods to monitor and quantitatively measure the health status of woodlands. These effects are especially notable in the Mediterranean area, where the decline of stands due to recurrent droughts has increased the damage caused by secondary pests whose populations would otherwise be in balance. Remote sensing technologies allow us to work on large surfaces with reasonable precision. In particular, new spectral indices obtained from high-resolution hyperspectral and thermal images have been shown to be good predictors for the early detection of physiological changes related to diseases. In this pilot study developed in a stand of Pinus halepensis in the Comunitat Valenciana, a controlled simulation of a decay is carried out by means of sequential girdling of trees, making a subsequent field monitoring of the caused decay. Through a hyperspectral camera, the spectral information of each of these trees is analyzed in relation to their discoloration and state of observed decay. The proposed methodology allows the detection of affected trees three months before the appearance of visual symptoms, obtaining a precision higher than 0.9 with Random Forest and Support Vector Machine classifiers. The vegetation indices with better results were PRI, VGO1, VGO2, GM1 and OSAVI. This pilot study allows us to think that some of these indices can be used in the early detection of general pine wilt and, therefore, have application in the monitoring of the main threats to European forests, borer pests or quarantine organisms such as <em>Bursaphelenchus xylophilus.</em></p>

show abstract

Detection of Xylella fastidiosa infection symptoms with airborne multispectral and thermal imagery: Assessing bandset reduction performance from hyperspectral analysis

Cited by 79 publications

References 49 publications

Leaf hyperspectral reflectance as a potential tool to detect diseases associated with vineyard decline

Leaf hyperspectral reflectance as a potential tool to detect diseases associated with vineyard decline

Semi-Automatic Method for Early Detection of Xylella fastidiosa in Olive Trees Using UAV Multispectral Imagery and Geostatistical-Discriminant Analysis

Uso de imágenes hiperespectrales para la predicción del marchitamiento de Pinus halepensis (Mill.) en el bosque mediterráneo

Contact Info

Product

Resources

About