Error and Uncertainty Analysis in the Preparation of Thematic Maps using Artificial Neural Network and Environmental Data (A Case Study: Digital Soil Map of Shahrekord Plain)

Soil maps have considerable significance as basic maps in many environmental and natural resources studies. Digital soil maps are based on the relationship between environmental variables and soil properties. The main purpose of this research was to analyze error and uncertainty of digital soil classes predicted at different taxonomic levels of Soil Taxonomy system using an artificial neural network. One hundred and twenty soil profiles were described and sampled based on a regular grid scheme in Shahrekord plain. Two groups of soil properties (qualitative and quantitative) and auxiliary parameters (including geologic map, landform map, landform-phase map, traditional soil map, normalized difference vegetation index, and some derivatives of digital elevation model) were used to estimate soil classes. After preparing the soil properties maps and checking their accuracy, these maps were used along with auxiliary parameters for estimating soil classes using an artificial neural network model in the R software. Finally, the accuracy and uncertainty of the model were evaluated by overall accuracy and confusion index, respectively. Results showed that the entry of more details in the soils classification at the lower levels of the Soil Taxonomy system, while increasing the number of classes, leads to decreasing the overall accuracy and increasing uncertainty. It is noticeable that the artificial neural network model has a good accuracy up to the great group level through the acceptable level of overall accuracy (i.e., 75 %), hence it has a high degree of uncertainty. Therefore, the accuracy of the model could not be effective in its selection trough the modeling process; however, paying attention to its uncertainty is also very important along with the model error. Accordingly, we suggest using the other methods of soft computing for modeling in plain areas or in low relief regions.