Hyperspectral discrimination of foliar biotic damages in rice using principal component analysis and probabilistic neural network

Assessment of crop health status in real time could provide reliable and useful information for making effective and efficient management decisions regarding the appropriate time and method to control crop diseases and insect damage. In this study, hyperspectral reflectance of symptomatic and asymptomatic rice leaves infected by Pyricularia grisea Sacc, Bipolaris oryzae Shoem, Aphelenchoides besseyi Christie and Cnaphalocrocis medinalis Guen was measured in a laboratory within the 350–2 500 nm spectral region. Principal component analysis was performed to obtain the principal component spectra (PCs) of different transformations of the original spectra, including original ( R ), common logarithm of reciprocal (lg (1/ R )), and the first derivative of original and common logarithm of reciprocal spectra ( R ′ and (lg (1/ R ))′). A probabilistic neural network classifier was applied to discriminate the symptomatic rice leaves from asymptomatic ones with the front PCs. For identifying symptomatic and asymptomatic rice leaves, the mean overall discrimination accuracies for R , lg (1/ R ), R ′ and (lg (1/ R ))′ were 91.3, 93.1, 92.3 and 92%, and the mean Kappa coefficients were 0.771, 0.835, 0.829 and 0.82, respectively. To discriminate between disease and insect damage, the overall accuracies for R , lg (1/ R ), R ′ and (lg (1/ R ))′ were 97.7, 98.1, 100 and 100%, and the Kappa coefficients were 0.962, 0.97, 1 and 1, respectively. These results demonstrated that hyperspectral remote sensing can discriminate between multiple diseases and the insect damage of rice leaves under laboratory conditions.