Estimation of quantitative characteristics of Zagros forests using data mining ‎nonparametric algorithms (case study: Olad Ghobad Watershed, Koohdasht, Lorestan)‎

In this study, the effect of different cluster sampling schemes based on nonparametric algorithms to estimate the characteristics per hectare and canopy cover of customary Olad Ghobad forests located in Koohdasht city in the west of Lorestan province, were modeled using data Ground and satellite images of the Sentinel-2 To estimate the characteristics, 150 clusters in the form of six designs were implemented in a regular-random manner in the region. Then, six cluster sampling designs were collected inside the subplots, density characteristics, and canopy. Each cluster consisted of four sub-plots with an area of ​​700 square meters. After pre-processing the images and appropriate processing, the numerical values ​​corresponding to the ground sample parts were extracted from the spectral bands and considered as independent variables. Modeling was performed with 75% of the data and the results were evaluated with the remaining 25%. For both density characteristics (number per hectare) and canopy, artificial neural network method with squared percent mean square error and BIAS of 10.53, 2.48, 9.38% and 0.33% respectively in modeling have more accurate results than other methods used. In general, the use of different cluster sampling schemes, nonparametric modeling methods, and Sentinel-2 satellite images have good results in estimating the number of per hectare and canopy.