Abstract
Abstract. In this study grey-level co-occurrence matrix (GLCM) textures and a local statistical analysis Getis statistic (Gi), computed from IKONOS multispectral (MS) imagery acquired from the Yellow River Delta in China, along with a random forest (RF) classifier, were used to discriminate Robina pseudoacacia tree health levels. The different RF classification results of the three forest health conditions were created: (1) an overall accuracy (OA) of 79.5% produced using the four MS band reflectances only; (2) an OA of 97.1% created with the eight GLCM features calculated from IKONOS Band 4 with the optimal window size of 13 × 13 and direction 45°; (3) an OA of 94.0% created using the four Gi features calculated from the four IKONOS MS bands with the optimal distance value of 5 and Queen’s neighborhood rule; and (4) an OA of 96.9% created with the combined 16 spectral (four), spatial (four), and textural (eight) features. The experimental results demonstrate that (a) both textural and spatial information was more useful than spectral information in determining the Robina pseudoacacia forest health conditions; and (b) IKONOS NIR band was more powerful than visible bands in quantifying varying degree of forest crown dieback.
Highlights
Identifying the location and extent of forest at risk from damaging agents and processes assists forest managers in prioritizing their planning and operational mitigation activities (Haywood and Stone, 2011)
Since the textural and local spatial information has the potential to improving the accuracy of class designation by minimizing intra-class variation (Lévesque and King, 2003; Wulder and Boots, 1998), the overall objective of this study is to assess whether the grey-level co-occurrence matrix (GLCM) and Getis statistic (Gi) features extracted from IKONOS imagery were effective in determining Robinia pseudoacacia forest health conditions in the Yellow River Delta (YRD), China using random forest (RF) classifier
The reasons for choosing Band 4 to test the effects of the window size and direction on classifying forest health conditions include (1) the workload was too heavy to test all window sizes and directions for all four MS bands; (2) per statistics of training samples of Robinia pseudoacacia health conditions extracted from MS bands Band 4 was the most effective to discriminate among three health levels; and (3) Pu and Cheng (2015) supported that TM NIR band was the most important to correlate with LAI
Summary
Identifying the location and extent of forest at risk from damaging agents and processes assists forest managers in prioritizing their planning and operational mitigation activities (Haywood and Stone, 2011). With recent very high resolution (VHR) satellite imagery, such as QuickBird and IKONOS, forest stress and disease can be detected at a crown level (Lee and Cho, 2006), which makes discrimination of individual healthy and diseased trees possible (Coops et al, 2006). In stressed/diseased forest stands, the understory plants (e.g., regeneration forest, shrubs, and grasses) presenting in gaps and open areas may have a similar NIR response to a closed forest canopy. Such a classification challenge may be overcome by using grey-level co-occurrence matrix (GLCM) (Franklin et al, 2001) or Getis statistic (Gi) (Wulder and Boots, 2001; Myint et al, 2007; Ghimire et al, 2010)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
