A soft computing-based approach to spatio-temporal prediction

Rúbia E.O. Schultz, Tania M. Centeno, Gilles Selleron, Myriam R. Delgado
2009 International Journal of Approximate Reasoning  
This paper aims to incorporate intelligent mechanisms based on Soft Computing in Geographical Information Systems (GIS). The proposal here is to present a spatio-temporal prediction method of forestry evolution for a sequence of binary images by means of fuzzy inference systems (FIS), genetic algorithm (GA) and genetic programming (GP). The main inference is based on a fuzzy system which processes a set of crisp/fuzzy relations and infers a crisp relation representing the predicted image at a
more » ... edefined date. The fuzzy system is formed by a fixed fuzzy rule base and a partition set that may be defined by an expert or optimized by means of a GA. Genetic programming may also be adopted to generate the size of predicted area used in the final stage of the inference process. The developed methodology is applied in regions of Venezuela, France and Guatemala to identify their forestry evolution trends. The proposed approaches are compared with other techniques to validate the system. Geo-processing techniques are fundamental tools to assist decision-making in territorial-physical planning, as they allow the integration of spatial data from diverse sources and natures represented as information planes [3] . Some approaches described in the literature use a sequence of satellite images to generate a prediction for a specific region [1, 4] . Through the observation of thematic maps registered in different instants of time we can analyze the spatio-temporal behavior and forecast what is expected to happen for this region in the future. In [4] , the forestry prediction process is performed through the use of cellular automata. Such method was based on a situation map, acquired from a temporal sequence of satellite images, and describes the forest situation regarding progression, regression and stability zones. State transition rules between neighboring cells were used to generate predictions about the forest evolution. Many works have been developed based on fuzzy systems to solve problems related to geo-processing. According to Saint-Joan and Desachy [5] , fuzzy systems deal with imprecise and uncertain information in a more efficient way when compared with algebra maps systems based on Boolean logic. Many authors point out some advantages in the use of fuzzy inference systems to solve problems associated with environment [6-9]:
doi:10.1016/j.ijar.2008.01.010 fatcat:6v457zeyvffubggoua7ryzsxqu