Estimating Forest Canopy Cover in Black Locust (Robinia pseudoacacia L.) Plantations on the Loess Plateau Using Random Forest
文献类型：期刊论文
| 作者 | Wang, Fei ; Zhao, Jun; Zhou, Jingjing; Zhao, Zhong; Yu, Shichuan; Zhao, Qingxia
|
| 刊名 | FORESTS
 |
| 出版日期 | 2018-10-01 |
| 卷号 | 9期号:10页码:- |
| 关键词 | canopy cover (CC) spectral texture digital hemispherical photograph (DHP) random forest (RF) gray level co-occurrence matrix (GLCM) |
| ISSN号 | 1999-4907 |
| 文献子类 | Article |
| 英文摘要 | The forest canopy is the medium for energy and mass exchange between forest ecosystems and the atmosphere. Remote sensing techniques are more efficient and appropriate for estimating forest canopy cover (CC) than traditional methods, especially at large scales. In this study, we evaluated the CC of black locust plantations on the Loess Plateau using random forest (RF) regression models. The models were established using the relationships between digital hemispherical photograph (DHP) field data and variables that were calculated from satellite images. Three types of variables were calculated from the satellite data: spectral variables calculated from a multispectral image, textural variables calculated from a panchromatic image (T-pan) with a 15 x 15 window size, and textural variables calculated from spectral variables (TB+VIs) with a 9 x 9 window size. We compared different mtry and ntree values to find the most suitable parameters for the RF models. The results indicated that the RF model of spectral variables explained 57% (root mean square error (RMSE) = 0.06) of the variability in the field CC data. The soil-adjusted vegetation index (SAVI) and enhanced vegetation index (EVI) were more important than other spectral variables. The RF model of T-pan obtained higher accuracy (R-2 = 0.69, RMSE = 0.05) than the spectral variables, and the grey level co-occurrence matrix-based texture measureCorrelation (COR) was the most important variable for T-pan. The most accurate model was obtained from the TB+VIs (R-2 = 0.79, RMSE = 0.05), which combined spectral and textural information, thus providing a significant improvement in estimating CC. This model provided an effective approach for detecting the CC of black locust plantations on the Loess Plateau. |
| 源URL | [http://ir.rcees.ac.cn/handle/311016/40546]  |
| 专题 | 生态环境研究中心_城市与区域生态国家重点实验室 |
| 推荐引用方式 GB/T 7714 | Wang, Fei,Zhao, Jun,Zhou, Jingjing,et al. Estimating Forest Canopy Cover in Black Locust (Robinia pseudoacacia L.) Plantations on the Loess Plateau Using Random Forest[J]. FORESTS,2018,9(10):-. |
| APA | Wang, Fei,Zhao, Jun,Zhou, Jingjing,Zhao, Zhong,Yu, Shichuan,&Zhao, Qingxia.(2018).Estimating Forest Canopy Cover in Black Locust (Robinia pseudoacacia L.) Plantations on the Loess Plateau Using Random Forest.FORESTS,9(10),-. |
| MLA | Wang, Fei,et al."Estimating Forest Canopy Cover in Black Locust (Robinia pseudoacacia L.) Plantations on the Loess Plateau Using Random Forest".FORESTS 9.10(2018):-. |
入库方式： OAI收割
来源：生态环境研究中心
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。