Laurel wilt (Lw) is a fatal disease. It is a vascular pathogen and is considered a major threat\nto the avocado industry in Florida. Many of the symptoms of Lw resemble those that are caused\nby other diseases or stress factors. In this study, the best wavelengths with which to discriminate\nplants affected by Lw from stress factors were determined and classified. Visible-near infrared\n(400ââ?¬â??950 nm) spectral data from healthy trees and those with Lw, Phytophthora, or salinity damage\nwere collected using a handheld spectroradiometer. The total number of wavelengths was averaged\nin two ranges: 10 nm and 40 nm. Three classification methods, stepwise discriminant (STEPDISC)\nanalysis, multilayer perceptron (MLP), and radial basis function (RBF), were applied in the early stage\nof Lw infestation. The classification results obtained for MLP, with percent accuracy of classification\nas high as 98% were better than STEPDISC and RBF. The MLP neural network selected certain\nwavelengths that were crucial for correctly classifying healthy trees from those with stress trees. The\nresults showed that there were sufficient spectral differences between laurel wilt, healthy trees, and\ntrees that have other diseases; therefore, a remote sensing technique could diagnose Lw in the early\nstage of infestation.
Loading....