Remote Sensed Data Capacities to Assess Soil Degradation

This research has tried to take advantage of the two-field models in order to assess the remote sensing data capacities for modeling soil degradation. Based on the findings, pre-processing analysis types have not shown significant effect on accuracy of the model. Conversely type of field model used and its indicators and indices have a large impact on the accuracy of modeling. Also using some remote sensed indices such as Iron Oxide index and Ferrous Minerals index can help to improve the modeling accuracy of some field indices of soil condition assessment. According to the results, using time-series remote sensed data compared to the use of single date data can improve the model capacities significantly. Alse, if artificial neural networks used on single date remote sensed data instead of multivariate linear regression, accuracy of the model can be increased dramatically because it helps the model to take the form of nonlinear. However, if time series of remote sensed data used, the accuracy of the artificial neural network modeling is not much different than the accuracy of regression model. It turned out to be contrary to what is thought but according to the results, increasing the number of inputs to artificial neural network modeling in practice reduces the actual accuracy of the model.