Mapping individual tree health using full-waveform airborne laser scans and imaging spectroscopy: A case study for a floodplain eucalypt forest

详细信息    查看全文

• 作者：Iurii Shendryk^a ; ^{iurii.shendryk@unsw.edu.au} ; Mark Broich^a ; Mirela G. Tulbure^a ; Andrew McGrath^b ; David Keith^c ; ^d ; Sergey V. Alexandrov^e
• 关键词：Tree health ; Airborne laser scanning ; Imaging spectroscopy ; Random forest ; Object-oriented classification ; Australia ; Flooding frequency ; River red gum ; Dieback ; Eucalypt ; Individual trees
• 刊名：Remote Sensing of Environment
• 出版年：2016
• 出版时间：15 December 2016
• 年：2016
• 卷：187
• 期：Complete
• 页码：202-217
• 全文大小：2871 K
• 卷排序：187

文摘

We used ALS and IS for individual tree health mapping (i.e. dieback). We classified individual tree health with a kappa score of 0.66. ALS, followed by IS variables were the important predictors in classifications. Intensity and PCs were the most important ALS and IS variables, respectively. Tree dieback occurred primarily in areas that were infrequently flooded.