Estimation of forest leaf area index using satellite multispectral and synthetic aperture radar data in Iran

Different satellite datasets, including multispectral Sentinel 2 and synthetic aperture radar 1 ALOS2, were tested to estimate the Leaf Area Index (LAI) in Zagros forests, Ilam province, Iran. Field data collected 61 sample plots by hemispherical photographs, train validate LAI estimation models. combinations used as input regression models built with following algorithms: Multiple Linear Regression, Random Forests, Partial Least Square Regression. The results indicate that can be best estimated using integrated ALOS2 data; these inputs generated model higher accuracy (R2 = 0.84). combination of a single band vegetation index from also led successful 0.81). Lower was obtained when only ALOS 0.72), but this dataset is helpful where cloud coverage affects optical data. not useful for prediction. optimal based on traditional Regression algorithm, preliminary selection step exclude multicollinearity effects. To avoid step, use may an alternative, algorithm able produce estimates similar those model.