基于ASTER遥感数据的杨树林分因子建模及制图研究

A Study on Modeling & Mapping for Poplar Stands' Parameters Based on ASTER Remote Sensed Datasets

利用ASTER原始的9个波段数据进行主成分、小波、MNF、RBV等图像融合和变换生成37个特征波段,结合江苏苏北平原建湖县48个杨树样地调查数据,分别就杨树平均高、年龄和单位面积蓄积量进行传统的统计建模分析,并在数据挖掘软件Cubist支持下研究了回归树建模。对比两次分析发现,因为利用回归树建立的遥感估算模型总体精度优于传统的单输入模型,所以大地域遥感生物物理参数制图时采用回归树模型更为可行和可靠。

The methods of image fusion and transform, including PCA, wavelet-based fusion, MNF and RBV transform etc. were executed to generate 37 feature bands on the basis of the ASTER original 9 bands. Coupling with observations of 48 poplar sample plots, traditional univariate regression models and regression tree models for average height, age and stem volume of poplar were established respectively. After comparing the performance of models fitting and ground-truthing, it was found that regression tree models were superior to traditional univariate models in mapping spatial distribution of poplar stands＇ parameters. Consequently, taking regression tree models to retrieve and map biophysical variables at a regional scale based on remote sensed data was more viable and reliable.