Camellia oleifera leaf carbon nitrogen ratio estimation method based on canopy hyperspectrum

The invention relates to the technical field of oil-tea camellia leaf carbon-nitrogen ratio estimation, in particular to an oil-tea camellia leaf carbon-nitrogen ratio estimation method based on canopy hyperspectrum. According to the method, a multi-layer feedforward neural network based on error reverse propagation, namely a BP neural network, is utilized to construct an estimation model of the carbon-nitrogen ratio of the oil-tea camellia leaves and the visible light and near-infrared spectrum region hyperspectrum, and the measured canopy hyperspectrum of the oil-tea camellia to be measured is input into the estimation model to obtain the carbon-nitrogen ratio data of the oil-tea camellia leaves to be measured. According to the invention, the BP neural network algorithm is adopted to train and learn the carbon-nitrogen ratio of the tea-oil tree leaf and the hyperspectral characteristics of the canopy, potential hyperspectral response characteristics influencing the estimation of the carbon-nitrogen ratio of