Evaluation of ETM+ data applicability for remote sensing of the soil texture and vegetation effects on accuracy of predictions

Several investigations have been carried out in order to remote sensing of soil texture using radar data. Whereas there is no report on application of using passive and free satellites data including ETM+ and MODIS for this aspect. The remote sensing of soil texture also is limited by the existence of vegetation on soil surface. So the current research was aimed to evaluate ETM+ data applicability for remote sensing of the soil texture as well as assessment of the vegetation effects on the accuracy of the predictions. In this regard, soil separates were measured at 225 different points of study area on Northern slopes of Mount Sahand and available ETM+ data were downloaded. Several methods including empirical, statistical, and black box (artificial neuron network, ANN) using Excel, SPSS, and Matlab software’s were applied to create different functions for remote sensing of soil separates. Results showed that vegetation existence led to lower accuracy of the prediction. Results showed that although empirical and statistical approaches showed low accuracy (with R2 lower than 0.3) for remote sensing of the soil separates, black box model using ANN algorithm was accurate enough (with R2 higher than 0.5).