当前位置： 首页»科研成果» 2014 张玉珍等在IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING发表论文 全球院

 

Yuzhen Zhang, Shunlin Liang, Fellow, IEEE, and Guoqing Sun, Senior Member, IEEE

 

College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China;

Department of Geographical Science, University of Maryland, College Park, MD 20742 USA.

 

ABSTRACT

In this study, several major issues associated with forest biomass mapping have been investigated using an integrated dataset, and a preliminary forest biomass map of northeastern China is presented. Three biomass regression models, stepwise regression (SR), partial least-squares regression (PLSR), and support vector regression (SVR), were developed based on field biomass data, Geoscience Laser Altimeter System (GLAS) data, and Moderate Resolution Imaging Spectroradiometer (MODIS) data. The biomass estimates using the SVR model were the most reasonable. The accuracy of the biomass predictions was improved through a combination of bootstrapping and the SVR method. The rich temporal information in MODIS data and the multiple-angle information in Multi-angle Imaging Spectro Radiometer (MISR) data were also explored for forest biomass mapping. Results indicated that a MODIS time series data alone, without MISR data, was capable of mapping forest biomass. A forest biomass map was generated using the optimal biomass regression model and the MODIS time series data. Finally, an uncertainty analysis of the biomass map was carried out and a comparison with published results using other methods was made.

 

KEY WORDS: Forest biomass mapping, Geoscience Laser Altimeter System (GLAS) data, random forests, support vector regression

 

PUBLISHED BY: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (1): 140-152.

 

SOURCE: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6507553&sortType=asc_p_Sequence&filter=AND(p_IS_Number:6689357)