Monitoring Cadmium Content in the Leaves of Field Pepper and Eggplant in a Karst Area Using Hyperspectral Remote Sensing Data

The ability to quickly and non-destructively monitor the cadmium (Cd) content in agricultural crops is basic premise of effective prevention control Cd contamination products. Hyperspectral technology provides a solution for this issue. potential capability spectral prediction leaves pepper eggplant field was explored, model these established. In study, based on indoor spectrum, sensitive wavebands predicting were determined preliminarily by correlation analysis. Partial least squares regression (PLSR) support vector machine (SVMR) used establish models, final size index. results show that SVMR exhibited higher accuracy than PLSR model. RPDp (relative percent different set) values best models 1.82 1.49, respectively. Rp2 (coefficient determination set), which can quantitatively estimate leaves, 0.897 (p < 0.01) 0.726 0.01), This study demonstrated leaf spectra be predict providing reference monitoring fruits future.