Rice leaf soluble sugar content remote sensing inversion model and method based on fixed-radius nearest neighbor regression algorithm

Abstract

The invention provides a rice leaf soluble sugar content remote sensing inversion model based on a fixed-radius nearest neighbor regression algorithm, which is a fixed-radius nearest neighbor regression model of Python language and further provides model parameters of the fixed-radius nearest neighbor regression model. The invention further provides a rice leaf soluble sugar content remote sensinginversion method based on the fixed radius nearest neighbor regression algorithm. According to the rice leaf soluble sugar content remote sensing inversion model based on the fixed radius nearest neighbor regression algorithm, the rice leaf soluble sugar content information can be rapidly and accurately obtained, the difficulty that the characteristic wave band of the rice leaf soluble sugar content is difficult to determine due to the spectral superposition effect caused by complex rice components is overcome, and model result divergence caused by unbalanced training data is reduced, so thatthe precision of the rice leaf soluble sugar content inversion model is improved.

Description

technical field [0001] The invention relates to the technical field of agricultural remote sensing, in particular to the technical field of measuring the soluble sugar content of rice leaves, and specifically refers to a remote sensing inversion model and method for the soluble sugar content of rice leaves based on a fixed-radius nearest neighbor regression algorithm. Background technique [0002] The soluble sugar content of rice leaves refers to the content of soluble sugars such as glucose and sucrose in rice leaves. Soluble sugar content is an important parameter to quantify rice photosynthesis to fix carbon dioxide and synthesize carbohydrates. At the same time, soluble sugar plays an important regulatory role in the life cycle of plants. It not only provides energy and metabolic intermediates for the growth and development of rice, but also has important signaling functions. It is an important regulator of rice growth and gene expression. The signal constitutes a comp...

AI Technical Summary

Problems solved by technology

In the process of constructing the inversion model of rice leaf soluble sugar content, the spectral range measured by the full-band spectrometer covers 350nm to 1100nm, but due to the complexity of rice components, the spectral characteristic bands of the components overlap partially, and the characteristic spectrum of rice leaf soluble sugar content At the same time, the rapid processing of hyperspectral data has become an urgent technical problem to estimate the soluble sugar content of rice leaves based on hyperspectral data

In addition, the collected soluble sugar content and hyperspectral data of rice leaves may have a data distribution that does not completely conform to the normal distribution, or even an unbalanced distribution, which will lead to divergence of the model results and large errors

[0005] Therefore, it is hoped to provide a remote sensing inversion model of rice leaf soluble sugar content, which can quickly and accurately obtain the information of rice leaf soluble sugar content, and overcome the characteristic bands of rice leaf soluble sugar content caused by the spectral superposition effect caused by the complexity of rice components. Difficulties that are difficult to determine, reduce the divergence of model results caused by unbalanced training data, thereby improving the accuracy of the inversion model for rice leaf soluble sugar content

Images