Nonlinear partial least square optimizing model-based forest carbon sink remote sensing evaluation method

Abstract

The invention relates to a nonlinear partial least square optimizing model-based forest carbon sink remote sensing evaluation method which comprises the following main steps of: (1) mapping the original variable to a high-dimension space to obtain a new variable by adopting a kernel function and carrying out standardization treatment; (2) carrying out regression analysis on the extracted component by adopting a least square method and reducing a regression coefficient; (3) evaluating a model by adopting LOO cross effectiveness; (4) repeating the step (2) to step (3) and adding 1 to the component number every repetition till the extracted component number reaches the maximal value; (5) repeating the step (1) to the step (4) and adding 1 to the subsection number M in the step (1) every repetition till M is equal to the preset number; and (6) searching the model with maximal related coefficient of an estimating value and a practical value from all the models and modeling with the M and extracted component number at the moment for being used as a final estimation model. The invention uses the optimized nonlinear partial least square regression for establishing a forest carbon storage predicting model and improves the forest carbon storage predicting precision.

Description

【Technical field】 [0001] The invention relates to a forest carbon sink remote sensing estimation method based on a statistical optimization model. 【Background technique】 [0002] Forests are an important part of the global carbon balance and play a key role in the terrestrial carbon cycle. Therefore, accurate estimation of forest carbon storage is of great significance for the study of global change. Bamboo forest is a special forest type in subtropical regions of China (such as Zhejiang, Anhui, Jiangxi, Fujian and other provinces). Recent studies have shown that bamboo forest resources have huge carbon storage, and its contribution to global carbon balance has begun to attract attention. [0003] Remote sensing is an important means of estimating aboveground carbon storage in forests. However, remote sensing technology cannot directly measure biomass, carbon storage and their changes. It requires a series of processing and conversion of remote sensing observation data, and ...

AI Technical Summary

Problems solved by technology

[0004] Multiple linear regression based on ordinary least squares assumes that there is a linear relationship between remote sensing data and biophysical attributes, and assumes that the independent variables (spectral bands of remote sensing data) are independent, but most of the spectral responses of biophysical attributes are curvilinear, and there is a high relationship between the bands. Therefore, the regression analysis is often difficult to meet the basic assumptions, resulting in inaccurate estimates; in addition, if there are measurement errors in the spectral reflectance and biophysical attribute variables, the ordinary least squares regression may get a wrong model, but the spectral Albedo and biophysical property variables are not possible without error

Images