Improvement of LCC prediction modeling based on correlated parameters and model structure uncertainty propagation

Citations of this article
Mendeley users who have this article in their library.
Get full text


Land cover change (LCC) mapping is one of the basic tasks for environmental monitoring and management. The most significant factors in determining the performance of model of LCC prediction are its structure and parameter optimization. However, these factors are generally marred by uncertainties which affect the reliability of decision about changes. The reduction of these uncertainties is deemed as essential elements for LCC prediction modeling. Propagation of uncertainty appears as good alternative for decreasing the uncertainty related to LCC prediction process and therefore obtain more relevant decision. On the other hand, correlation analysis between model parameters is often neglected. This affects the reliability of the model and makes it difficult to better determine the uncertainty related to model parameters. Several studies in literature depicts that evidence theory can be applied to propagate uncertainty associated to LCC prediction models and to solve multidimensional problems. This paper presents an effective optimization scheme for the LCC prediction modeling based on the uncertainty propagation of model parameters and model structure. Uncertainty propagation is analyzed by using evidence theory without and with considering correlations. In this study, change prediction of land cover in Saint-Denis City, Reunion Island of next 5 years (2016) was anticipated using multitemporal Spot-4 satellite images acquired at the dates 2006 and 2011. Results show good performances of the proposed approach in improving prediction of the LCC. Results also demonstrate that the proposed approach is an effective and efficient method due to its adequate degree of accuracy.




Ferchichi, A., Boulila, W., & Farah, I. R. (2017). Improvement of LCC prediction modeling based on correlated parameters and model structure uncertainty propagation. In Studies in Computational Intelligence (Vol. 669, pp. 270–290). Springer Verlag.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free