Rice leaf starch content remote sensing inversion model and method based on XGBoost regression algorithm

Abstract

The invention provides a rice leaf starch content remote sensing inversion model based on an XGBoost regression algorithm, which is an XGBoost regression model of Python language, and further provides model parameters of the XGBoost regression model. The invention further provides a rice leaf starch content remote sensing inversion method based on the XGBoost regression algorithm. The rice leaf starch content remote sensing inversion model based on the XGBoost regression algorithm can quickly and accurately obtain the rice leaf starch content information, and overcomes the difficulty that the characteristic waveband of the rice leaf starch content is difficult to determine due to the spectral superposition effect caused by complex rice components; The precision of the rice leaf starch content inversion model is greatly improved; the rice leaf starch content inversion model is ingenious in design, simple and convenient to calculate, easy to implement, low in cost and suitable for large-scale popularization and application.

Description

technical field [0001] The invention relates to the technical field of agricultural remote sensing, in particular to the technical field of rice leaf starch content measurement, and specifically refers to a remote sensing inversion model and method for rice leaf starch content based on an XGBoost regression algorithm. Background technique [0002] Starch content in rice leaves refers to the weight percentage of starch in rice leaves. It is an important parameter to quantify the photosynthesis state of rice, carbon dioxide fixation, and carbohydrate synthesis. It reflects rice physiology, growth, and fertilizer and water conditions. The influence of factors such as fertilizer and water. [0003] Monitoring the starch content of rice leaves and mastering the physiological conditions and growth conditions of rice photosynthetic products such as synthesis, transport, storage and accumulation can not only ensure the yield and quality of rice production, but also dynamically manag...

AI Technical Summary

Problems solved by technology

In the process of constructing the inversion model of rice leaf starch content, the spectral range measured by the full-band spectrometer covers 350nm to 2500nm, but due to the complexity of rice components, the spectral characteristic bands of the components overlap partially, and the determination of the characteristic spectrum of rice leaf starch content At the same time, the rapid processing of hyperspectral data has become an urgent technical problem to estimate the starch content of ric

Images