Multistrategy fuzzy learning for multisource remote sensing classifiers

This paper presents a multistrategy fuzzy learning method to the generation and refinement of multisource remote sensing classification rules. The learning procedure uses theoretical knowledge in the form of fuzzy production rules and a set of training examples, or pixels, assigned to fuzzy classes to develop a method for accurately classifying pixels not seen during training. The strategy is organised to preserve the advantages of direct elicitation techniques and empirical learning strategies while avoiding the disadvantages these present when used as monostrategy learning method. The performance of the methodology has been evaluated applying it to the actual environmental problem of fire risk mapping in Mediterranean areas, using an approach in which information describing risk factors are mainly extracted, by means of classification procedures, from satellite remotely sensed images (Landsat TM, SPOT PAN). Results achieved, quantitatively and qualitatively evaluated by experts, proves that the method proposed provides adequate solutions for multiple feature evaluation and accurate discrimination between coexisting borderline cases, which generally are main problems when dealing with multisource remote sensing classification tasks.