Land cover dynamics influence the spatio-temporal evolution of the Rural-Urban Interface (RUI). This represents the most prone area for human-caused forest fires ignitions in Mediterranean countries. Traditionally, RUI mapping is based on the measurement of the distances among specific land covers. This methodology suffers from the definition of pre-established fixed parameters. To avoid this arbitrariness, a new procedure based on Multilayer Perceptron and Fuzzy Set Theory is introduced in this paper. This allows to develop continuous non-categorical maps expressing the possibility of being part of this interface. Thus, an innovative way for assessing the uncertainty in identifying RUI is presented. The proposed methodology has been applied to the case study of Portugal, elaborating a future scenario for the RUI. The results show how the framework proposed in this paper is able to correctly identify the areas belonging to this interface, providing useful information for forest fires -prevention policies.