Improvement of Forest Canopy Density Mapping of Spare Forests Using a Novel RS-GIS Based Classification Method [post]

Mohammad Hassan Naseri, Shaban Shataee
2021 unpublished
Background: Accurate mapping and monitoring canopy cover using remote sensing data as an alternative way for field surveys are very important for forest managers, particularly in the spare and low dense forests. Due to being area-based of canopy cover density and mixing spectral responses of tree crowns and soil in the thin and semi-dense forests, finding the high-performance method of classification is a challenge particularly on high-resolution imagery. In this study, we compared produced
more » ... of canopy cover using direct remote sensing and indirect (RS-GIS-based) methods in two forest sites on the Quickbird and WorldView-2 images using the Artificial Neural Network (ANN) algorithm. Also, the optimal plot area was examined by different plot areas.Results: In the direct method and based on the obtained results, in the Dashte Barm using Quickbird image, the best classification was for plots of 7500 m2 with an overall accuracy of 56.57% and kappa coefficient of 0.32. In the Ilam site and on the WorldView-2 image, the best result is obtained by the plots of 5,000 m2 area with an overall accuracy of 45.71% and the kappa coefficient of 0.263. The results of accuracy assessment of maps of indirect method in the Dashte Barm site for grids with different areas showed that the best classifications obtained from sample plot areas of 10000 m2 with overall accuracy of 82.69% and Kappa coefficient of 0.744; but in the Ilam sites the best result was obtained using sample area of 1000 m2 with overall accuracy of 74.27% and the Kappa coefficient of 0.690. Conclusions: The results exposed that use of the RS-GIS based method could considerably improve the results compare to direct classification. Also, the results showed concerning the conditions of canopy cover density of forest stands, plots with different areas can be used to map of forest canopy cover density; however, for direct classification the use of plots with areas of 5000 m2 and more are suitable in sparse forests. For RS-GIS based method, the plot areas of 1000 m2 are optimal due to time and cost saving.
doi:10.21203/ fatcat:6qdsy6bsjfacxicrztbnxs2alu