Huanglongbing (HLB) or citrus greening is a bacterial disease threatening Florida’s multi-billion dollar citrus industry. Currently, the best management practice to control the disease is to detect the infected tree and remove it as soon as possible as the infected tree can be the inoculum source resulting in further spread of the disease. Scouting and visual inspection for the disease symptoms is currently used by growers to identify HLB-infected trees. However, this method is very time consuming, subjective, and expensive. Therefore, the long-term goal of this research is to develop a fast screening technique that can assist citrus growers in detecting HLB-infected citrus trees. In this study, a rugged, low-cost, multi-band active optical sensor and hyperspectral imaging were used to identify HLB-infected trees from healthy trees. Analysis of the multi-band optical sensor data showed that due to the large variability in the data, it was not possible to discriminate the healthy trees from that of infected trees based only on a single measurement from a tree. However, using multiple measurements from a tree, it was possible to achieve high classification accuracy. With three measurements, k-nearest neighbors and support vector machines yielded classification errors of less than 5%. Normalized Difference Vegetation Index (NDVI), Simple Ratio Index (SR), Modified Triangular Vegetation Index (MTVI-2), Renormalized Difference Vegetation Index (RDVI) and Structure Intensive Pigment Index (SIPI) are indices that were evaluated for healthy and HLB infected trees based on the optical sensor and hyperspectral imaging results. These vegetative indices showed potential to differentiate HLB trees from healthy trees with multi band optical sensor as well as hyperspectral camera. The results demonstrate the potential of a multi-band active optical sensor and hyperspectral camera for detecting HLB-infected citrus trees under field conditions.
[1]
John R. Miller,et al.
Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture
,
2004
.
[2]
John C. Platt,et al.
Fast training of support vector machines using sequential minimal optimization, advances in kernel methods
,
1999
.
[3]
G. Carter,et al.
Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration.
,
2001,
American journal of botany.
[4]
J. Roujean,et al.
Estimating PAR absorbed by vegetation from bidirectional reflectance measurements
,
1995
.
[5]
K L Manjunath,et al.
Detection of 'Candidatus Liberibacter asiaticus' in Diaphorina citri and its importance in the management of citrus huanglongbing in Florida.
,
2008,
Phytopathology.
[6]
Keinosuke Fukunaga,et al.
Introduction to statistical pattern recognition (2nd ed.)
,
1990
.
[7]
Moon S. Kim,et al.
Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance
,
2000
.
[8]
N. Broge,et al.
Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density
,
2001
.
[9]
M. Irey,et al.
Determining HLB Infection Levels using Multiple Survey Methods in Florida Citrus
,
2009
.
[10]
Daniel T. Larose,et al.
Data mining methods and models
,
2006
.
[11]
I. Filella,et al.
Reflectance assessment of mite effects on apple trees
,
1995
.