Rice leaf starch accumulation remote sensing inversion model and method based on ElasticNet regression algorithm

Abstract

The invention provides a rice leaf starch accumulation amount remote sensing inversion model based on an ElasticNet regression algorithm, the rice leaf starch accumulation amount remote sensing inversion model is an ElasticNet regression model of a Python language, and model parameters of the ElasticNet regression model are further provided. The invention further provides a rice leaf starch accumulation amount remote sensing inversion method based on the ElasticNet regression algorithm. The rice leaf starch accumulation amount remote sensing inversion model based on the ElasticNet regression algorithm can rapidly and accurately obtain rice leaf starch accumulation amount information, overcomes the difficulty that the characteristic wave band of the rice leaf starch accumulation amount is difficult to determine due to the spectral superposition effect caused by complex rice components, reduces the model overfitting phenomenon caused by correlation or colinearity of data of adjacent andsimilar wave bands of high-resolution spectral data, and greatly improves the precision of the rice leaf starch accumulation inversion model.

Description

technical field [0001] The invention relates to the technical field of agricultural remote sensing, in particular to the technical field of measuring rice leaf starch accumulation, and specifically refers to a remote sensing inversion model and method for rice leaf starch accumulation based on an ElasticNet regression algorithm. Background technique [0002] Starch accumulation in rice leaves is an important parameter for quantifying rice photosynthesis to fix carbon dioxide and synthesize carbohydrates. It is affected by factors such as rice photosynthetic capacity, environmental temperature, and fertilizer and water, and reflects the physiological status, growth activity, and external fertilizer and water management measures of rice. Influence of growth status. [0003] Monitoring the accumulation of starch in rice leaves, grasping the physiological conditions and growth conditions of rice photosynthetic products such as synthesis, transport, storage, and accumulation can ...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings in the above-mentioned prior art, an object of the present invention is to provide a remote sensing inversion model of rice leaf starch accumulation based on the ElasticNet regression algorithm, which can quickly and accurately obtain the information of rice leaf starch accumulation, and overcome the problem of rice leaf starch accumulation. The spectral superposition effect caused by complex components makes it difficult to determine the characteristic bands of starch accumulation in rice leaves, and reduces the correlation or collinearity of high-resolution spectral data adjacent to similar band data or the model overfitting phenomenon caused by collinearity. Improving the accuracy of the inversion model of starch accumulation in rice leaves, suitable for large-scale application

Images