using a combination of optical and radar imagery for pasture classification

remote sensing can be used as a powerful tool by using data from different sources and combine them for vegetation and land cover classification. pasture type classification provides key information for analysis of agricultural productivity, carbon accounting and biodiversity. the first data set that used in this study landsat tm (thematic mapper) optical image and the second envisat asar radar image for the study area located within the north-west of tehran (south alborz). in this study after applying several methods which all of them are non- lambertian and regarding to evaluate them, topographic correction was performed for optical image. the usefulness and improvement of using texture features extracted from optical and radar images in integration with spectral bands of the optical image has been evaluated on the final classification results and genetic algorithm used to select features that are independent to derive the most accurate results. in another part of the study, the impact of elevation data and optical image vegetation indices evaluated on final classification result and optimal bands selected. the results indicate increase in the overall accuracy and maximum likelihood kappa coefficient from 77.04 and 0.7317 for original optical image to 78.71 and 0.7495 in case of using genetic algorithm and 83.37 and 0.8036 in case of using elevation data and vegetation indices.