Satellite-based carbon stock estimation for bamboo forest with a non-linear partial least square regression technique |
| |
Authors: | Huaqiang Du Guomo Zhou Hongli Ge Wenyi Fan Xiaojun Xu Weiliang Fan |
| |
Affiliation: | 1. Zhejiang Provincial Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration, Zhejiang A &2. F University , Lin'an, 311300, China;3. School of Environmental Science and Technology, Zhejiang A &4. F University , Lin'an, 311300, China dhqrs@126.com;6. F University , Lin'an, 311300, China;7. Forest College, Northeast Forestry University , Harbin, Heilongjiang Province, 150040, China |
| |
Abstract: | This article explores a non-linear partial least square (NLPLS) regression method for bamboo forest carbon stock estimation based on Landsat Thematic Mapper (TM) data. Two schemes, leave-one-out (LOO) cross validation (scheme 1) and split sample validation (scheme 2), are used to build models. For each scheme, the NLPLS model is compared to a linear partial least square (LPLS) regression model and multivariant linear model based on ordinary least square (LOLS). This research indicates that an optimized NLPLS regression mode can substantially improve the estimation accuracy of Moso bamboo (Phyllostachys heterocycla var. pubescens) carbon stock, and it provides a new method for estimating biophysical variables by using remotely sensed data. |
| |
Keywords: | |
|
|