An Intelligent Possibilistic Approach to Reduce the Effect of the Imperfection Propagation on Land Cover Change Prediction

Abstract

The interpretation of satellite images in a spatiotemporal context is a challenging subject for remote sensing community. It helps predicting to make knowledge driven decisions. However, the process of land cover change (LCC) prediction is generally marred by imperfections which affect the reliability of decision about these changes. Propagation of imperfection helps improve the change prediction process and decrease the associated imperfections. In this paper, an imperfection propagation methodology of input parameters for LCC prediction model is presented based on possibility theory. The possibility theory has the ability to handle both aleatory and epistemic imperfection. The proposed approach is divided into three main steps: 1) an imperfection propagation step based on possibility theory is used to propagate the parameters imperfection, 2) a knowledge base based on machine learning algorithm is build to identify the reduction factors of all imperfection sources, and 3) a global sensitivity analysis step based on Sobol’s method is then used to find the most important imperfection sources of parameters. Compared with probability theory, the possibility theory for imperfection propagation is advantageous in reducing the error of LCC prediction of the regions of the Reunion Island. The results show that the proposed approach is an efficient method due to its adequate degree of accuracy.