Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging

Abstract

This study was carried out to investigate the potential of visible and near infrared (VIS–NIR) hyperspectral imaging system for rapid and non-destructive content determination and distribution estimation of nitrogen (N), phosphorus (P) and potassium (K) in oilseed rape leaves. Hyperspectral images of 140 leaf samples were acquired in the wavelength range of 380–1030 nm and their spectral data were extracted from the region of interest (ROI). Partial least square regression (PLSR) and least-squares support vector machines (LS-SVM) were applied to relate the nutrient content to the corresponding spectral data and reasonable estimation results were obtained. The regression coefficients of the resulted PLSR models with full range spectra were used to identify the effective wavelengths and reduce the high dimensionality of the hyperspectral data. LS-SVM model for N with RP of 0.882, LS-SVM model for P with RP of 0.710, and PLSR model for K with RP of 0.746 respectively got the best prediction performance for the determination of the content of these three macronutrients based on the effective wavelengths. Distribution maps of N, P and K content in rape leaves were generated by applying the optimal calibration models in each pixel of reduced hyperspectral images. The different colours represented indicated the change of nutrient content in the leaves under different fertiliser treatments. The results revealed that hyperspectral imaging is a promising technique to detect macronutrients within oilseed rape leaves non-destructively and could be applied to in situ detection in living plants.