Determinate ASTER Satellite Data Capability and Classification and Regression Tree and Random Forest Algorithm for Forest Type Mapping

Recognition equal units and segregation them and upshot planning per units most basic method for management forest units. Aim this study presentation and comparison classification and regression tree (CART) and random forest (RF) algorithm for forest type mapping using ASTER satellite data in district one didactic and research forest's darabkola. In start using inventory network 500* 350 m, take number 150 sample plat in over district. After accomplish Geometric correction and reduce atmospheric effect on image processing bands rationing, create general vegetation indices, principal component analysis and tesslatcap index. After extraction spectrum values relevant by sample plats fabric and processing bands, classification values other pixel accomplish using investigating algorithms. Evaluation accuracy results classification accomplish by some sample plat that not participate in process classification. The result showed preparation map using RF with overall accuracy 66% and kappa coefficient 0.57 than classification and regression tree with overall accuracy 58% and kappa coefficient 0.49 has superior accuracy. Totality result showed using above algorithm may increased accuracy forest type map.