Abstract: Abstract: Citrus greening is a devastating disease of citrus fruit trees, and at present, it is potential for greening diagnosis by hyperspectral imaging technique. The purpose of this paper is to explore the feasibility of diagnosis and classification of greening using hyperspectral technique, and provide the reference for practical application of high-dimensional data. The hyperspectral images of citrus leaves were collected and divided into 5 types: slight greening, moderate greening, serious greening, nutrient deficiency and normal by common PCR (polymerase chain reaction). The samples of normal, nutrient deficiency, slight, moderate and serious greening show bright band in turn and the bright band colors are getting brighter with the grade of the disease. The bright band of nutrient deficiency samples by PCR is more vague than the greening samples, which may be related to the lack of nutrient elements. A total of 169 samples are divided into the calibration and prediction set for calibrating the models and accessing their performance respectively according to the proportion of 3:1. The calibration set includes 25 slight citrus greening samples, 21 moderate citrus greening samples, 26 serious citrus greening samples, 26 nutrient deficiency samples and 29 normal samples. The prediction set includes 6 slight citrus greening samples, 13 moderate citrus greening samples, 6 serious citrus greening samples, 10 nutrient deficiency samples and 7 normal samples. From the representative pictures of the 5 kinds of leaves, it can be seen intuitively that the leaves of greening present similar symptoms with the nutrient deficiency leaves, which are obviously different from the normal leaves. But it is difficult to distinguish between the leaves with slight, moderate, serious greening and nutrient deficiency. The average spectrum of hyperspectral images of leaves is extracted in the region of interest. The results show that strong reflection peak of chlorophyll is located at 550 nm, and greening hinders plant photosynthesis, resulting in the reflection peak of the leaves is significantly higher than the normal leaves; another more obvious reflection peak is at the 720 nm original hyperspectral spectrum, which is mainly caused by 4 frequency doubling stretching vibration of O-H. Due to the low water content of the leaves of greening, the reflection peak is lower than the normal leaves, and decreases gradually with the grade of the disease, and the reflection peak of leaves with serious greening is the lowest. The reflection peaks of leaves with nutrient deficiency may be caused by the lack of nutrient elements such as iron, nitrogen and zinc. The irrelevant information is eliminated by uninformative variable elimination (UVE), and genetic algorithm (GA) and continuous projection algorithm (SPA) are combined to screen the variables for data dimensionality reduction. Combining extreme learning machine (ELM) and least squares - support vector machine (LS-SVM), the discrimination model for citrus greening is developed. Diagnosis and classification are carried out for the predicted samples to evaluate the discrimination ability of the model. The results show that the effect of LS-SVM model with input variables screened by UVE combined with SPA is the best. At this time, the Link_kernel function is the kernel function of this model, the least punishment factor is 1.07, The lowest misjudgment rate is 0. The LS-SVM model has the highest degree of complexity and the worst prediction ability with the full spectrum as input variables, the highest misjudgment rate is 11.9%, which may be caused by the useless information and redundant information variables.. The results show that it is feasible to diagnose and classify citrus greening with LS-SVM using hyperspectral technique, whose input variables were screened using the combination of UVE and SPA, and the reference value is provided for the practical application of high-dimensional data.