Mohammad Reza Ahmadzadeh - School of Electronic Technology, Shiraz University
Maria Petrou - Informatics and Telematics Institute, CERTH, PO Box ۳۶۱, ۵۷۰۰۱, Thermi, Thessaloniki, Greece, and School of Electronics and Physical Sciences, University of Surrey, Guildford GU۲ ۷XH, UK

Fusion of spatial remote sensing data (slope, aspect, soil depth and rock permeability) to assess the risk of desertification of a burned forest by an expert system is studied. Belief functions which are assigned to data classes are propagated through expert rules. Uncertainty in the data because of sub-sampling error and uncertainty in the rules are considered during the processes. Experiments show the effectiveness of taking into consideration the uncertainty in data and rules

Remote Sensing, Dempster-Shafer Theory, Belief Propagation, Expert Systems