Estimation of Forest Crown Density Using Pleiades Satellite Data and Nonparametric Classification Method

The Zagros forests in western Iran are a crucial source of environmental services, but are severely threatened by climatic and anthropological constraints. One crucial forest parameter is the amount of canopy coverage which enables an indirect assessment of aboveground biomass and, in turn, the carbon emission and sequestration. The aim of this study is estimation of forest crown density using Pleiades satellite data and three non-parametric classification include random forest (RF), boosted regression tree (BRT) and classification and regression tree (CART) in Kaka Reza of Lorestan province, western Iran. For this purpose, we then ensured the accuracy of geometric images, creating the necessary processing such as vegetation indices, principal component analysis and texture analysis was performed on the original bands using a random—systematic sampling design, 96 sample plots were taken. Results showed that RF compared to the two other algorithms with overall accuracy of 75% and kappa coefficient of 0.73 could better classify the forest crown density, while the CART method had the lowest accuracy with overall accuracy of 71% and kappa coefficient of 0.68. Also results showed BRT had overall accuracy of 71% and kappa coefficient of 0.68. Overall results showed Pleiades satellite data and non-parametric classification method had high capability for separation crown density in Zagros region.