| 基于主成分回归及遥感的贵阳市林分郁闭度估测 |
| |
| 引用本文： | 蒋维成.基于主成分回归及遥感的贵阳市林分郁闭度估测[J].林业调查规划,2020,45(3):6-9,23. |
| |
| 作者姓名： | 蒋维成 |
| |
| 作者单位： | 贵州省林业调查规划院,贵州 贵阳 550003 |
| |
| 摘 要： | 以贵阳市为研究区,以Landsat-8 OLI为遥感信息源,通过偏相关分析,选择了与郁闭度相关的12个遥感因子作为自变量因子。为克服自变量因子间严重的多重共线性和模型的不稳定性,采用主成分回归分析法建立郁闭度估测模型,并对模型进了检验及精度验证。结果表明,回归方程调整后的R2=0.756,模型的拟合效果较好,说明模型在数学上是可行的;利用15个实测样地对模型进行精度验证,估测精度的平均水平为78.80%,说明该模型可为区域林分郁闭度估测提供参考。
|
| 关 键 词： | Landsat-8 OLI 卫星影像 遥感 郁闭度估测模型 主成分回归 |
Estimation of Forest Canopy Density in Guiyang City Based on Principal Component Regression and Remote Sensing |
| |
| JIANG Weicheng.Estimation of Forest Canopy Density in Guiyang City Based on Principal Component Regression and Remote Sensing[J].Forest Inventory and Planning,2020,45(3):6-9,23. |
| |
| Authors: | JIANG Weicheng |
| |
| Institution: | (Guizhou Institute of Forest Inventory and Planning,Guiyang 550003,China) |
| |
| Abstract: | Taking Guiyang City as the research area and Landsat-8 OLI as the remote sensing information source,12 remote sensing factors related to canopy density were selected as independent variable factors through partial correlation analysis.In order to overcome the serious multicollinearity between the independent variables and the instability of the model,the principal component regression analysis method was used to establish the estimation model of canopy density,and the model was tested and the accuracy was verified.The results showed that the adjusted R2=0.756,and the fitting effect of the model was good,indicating that the model was feasible in mathematics.The average level of the estimation accuracy was78.80%by using 15 sample plots to test the accuracy of the model,which could provide the reference for the estimation of regional forest canopy density. |
| |
| Keywords: | Landsat-8 OLI satellite image remote sensing model of canopy density estimation principal component regression |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
