Diagnosis the dust pollution stress of wheat leaves based on hyperspectral technology

Wheat leaves under different dust stress intensity were diagnosed with hyperspctrectral technology. A four-level dust stress experiment was conducted using the wheat in growing season as the study object. The spectra of wheat leaves which suffered different stress intensity levels,including severe stress, moderate stress, mild stress and no stress, were collected by ASD FieldSpec®3 spectrometer, and 32 samples were used for each level. All of the samples were divided randomly into two groups, one group with 96 ones used as calibrated set, and another with 32 ones as validated set. The spectra data were then pretreated by the methods of S.Golay smoothing and standard normal variable (SNV), and then the pretreated spectra data were analyzed with principal component analysis (PCA). Using the anterior 6 principal components computed by PCA as the model input variables, and the values of stress level as the output variables, the hyperspectral diagnosis models of dust stress intensity were established. And then the 32 unknown samples in the validated set were predicted by the diagnosis model. The result showed that the accuracy of model prediction was 87.5%, indicated it was feasible to diagnose the dust stress intensity with hyperspctral technology.