Establishment And Application Research Of Citrus Spectral Database

Characteristics such as sexual compatibility, related genera, the high frequency of bud mutations, the long history of cultivation and wide dispersion make it very rich in citrus germplasm. On the other hand, it is quite complicated, controversial and confusing in citrus germplasm identification, taxonomic and phylogenetic relationships. Spectroscopy technique is a powerful technique widely used in quantitative and qualitative analysis of materials. The technique is cheap and simple to use, requires very small amount of sample, and can achieve a rapid and highly sensitive measurement. Therefore, the use of spectroscopy technique to achieve the citrus classification, relationship identification and species identification is extremely important. On the other hand, developing citrus spectral database to achieve the collection, storage and management of spectral data of different varieties of citrus is the base of the spectroscopy technique used in qualitative analysis of citrus.In this study, spectral data of flowers, leaves and fruits of citrus were obtained, in conjunction with PHP and MySQL technology, citrus spectral database was established. Soft independent modeling of class analogy (SIMCA), partial least square discriminate analysis (PLS-DA), back propagation neural network (BPNN) and least squares-support vector machine (LS-SVM) were used to analysis spectral characteristics of different varieties of flowers, leaves and fruits of citrus and to develop a rapid and reliable method for the identification of citrus cultivars. The main work and achievements are as follows:1. Based on PHP+MySQL technology and asynchronous AJAX technology, a citrus spectral database was built. The database was user-friendly and with functions of spectral data storage, management, query and display.2. Applied researches of citrus spectral database:(1) Analysis of phylogenetic relationships of main citrus germplasms based on FTIR spectra of petals. To develop a quick, accurate and reliable technique for studying phylogenetic relationship of citrus, fourier transform infrared spectroscopy (FTIR) technique was used. The petals spectra of eighteen varieties of citrus germplasms were investigated by FTIR. Pretreatment methods of raw spectra (2000-500cm-1)were composed of baseline correction, normalize and first derivative (Savitzky-Golay). One-way ANOVA and Tukey’s HSD were used to extract effective wave bands, where the spectral absorbance values of different citrus germplasms were significantly different. The results showed that 2000-183 1cm11.1763-1595cm-1.1517-1090cm-1. 1035-1024cm-1,950-935cm-1,861-784cm-1,744-721cm-1 and 653-608 cm-1 were the effective wave bands. Hierarchical cluster analysis (HCA) was adopted to classify citrus germplasms based on the above eight effective wave bands. It was found that eighteen citrus varieties were classified into six subgroups. The results of classification and citrus phylogenetic relationships between six subgroups were consistent of results from Morphology, Biochemistry, Cytology and Molecular Biology. The overall results demonstrated that fourier transform infrared spectroscopy technique with One-way ANOVA and Tukey’s HSD and hierarchical cluster analysis model were promising for the rapid, accurate and reliable classification for citrus as well as studying citrus phylogenetic relationship.(2) Identification of citrus cultivars by using Vis/NIR spectra and pattern recognition methods. Vis/NIR spectroscopy was used in combination with pattern recognition methods to identify cultivars of pummelo. Soft independent modeling of class analogy (SIMCA), partial least square discriminate analysis (PLS-DA), back propagation neural network (BPNN) and least square support vector machine (LS-SVM) were performed on the spectral data. The results showed that discrimination accuracy more than 90%was achieved for both the BPNN and the LS-SVM models in the validation set, indicating that the performance of the two models was acceptable. Comparatively, the results of the PLS-DA and the SIMCA models were unacceptable for having lower discrimination accuracy. We also can see that the discrimination accuracy of LS-SVM models were the best. The overall results demonstrated that use of Vis/NIR spectroscopy coupled with the use of LS-SVM could achieve an accurate identification of pummelo cultivars.(3) Identification of citrus cultivars based on hyperspectral imaging technology. Existing methods for the identification of pummelo cultivars are usually time-consuming and costly, and are therefore inconvenient to be used in cases that a rapid identification is needed. This research was aimed at identifying different pummelo cultivars by hyperspectral imaging technology which can achieve a rapid and highly sensitive measurement. A total of 240 leaf samples,60 for each of the four cultivars were investigated. Samples were divided into two groups such as calibration set (48 samples of each cultivar) and validation set (12 samples of each cultivar) by a Kennard-Stone-based algorithm. Hyperspectral images of both adaxial and abaxial surfaces of each leaf were obtained, and were segmented into a region of interest (ROI) using a simple threshold. Spectra of leaf samples were extracted from ROI. To remove the absolute noises of the spectra, only the spectral range 400-1000 nm was used for analysis.Multiplicative scatter correction (MSC) and standard normal variable (SNV) were utilized for data preprocessing.Principal component analysis (PCA) was used to extract the best principal components, and successive projections algorithm (SPA) was used to extract the effective wavelengths. Least squares support vector machine (LS-SVM) was used to obtain the discrimination model of the four different pummelo cultivars. To find out the optimal values of σ2 and ywhich were important parameters inLS-SVM modeling, Grid-search technique and Cross-Validation were applied. The first 10 and 11 principal components were extracted by PCA for the hyperspectral data of adaxial surface and abaxial surface, respectively. There were 31 and 21 effective wavelengths selected by SPA based on the hyperspectral data of adaxial surface and abaxial surface, respectively. The best principal components and the effective wavelengths were used as inputs of LS-SVM models, and then the PCA-LS-SVM model and the SPA-LS-SVM model were built. The results showed that 99.46% and 98.44% of identification accuracy was achieved in the calibration set for the PCA-LS-SVM model and the SPA-LS-SVM model, respectively, and a 95.83% of identification accuracy was achieved in the validation set for both the PCA-LS-SVM and the SPA-LS-SVM models, which were built based on the hyperspectral data of adaxial surface. Comparatively, the results of the PCA-LS-SVM and the SPA-LS-SVM models built based on the hyperspectral data of abaxial surface both achieved identification accuracies of 100% for both calibration set and validation set. The overall results demonstrated that use of hyperspectral data of adaxial and abaxial leaf surfaces coupled with the use of PCA-LS-SVM and the SPA-LS-SVM could achieve an accurate identification of pummelo cultivars. It was feasible to use hyperspectral imaging technology to identify different pummelo cultivars, and hyperspectral imaging technology provided an alternate way of rapid identification of pummelo cultivars. Moreover, the results in this paper demonstrated that the data from the abaxial surface of leaf was more sensitive in identifying pummelo cultivars. This study provided a new method for to the fast discrimination of pummelo cultivars.