Markov chains and cellular automata to predict environments subject to desertification

Abstract

The foremost objective of this study was to analyze the performance of a Markov chain/cellular automata model for predicting land use/land cover changes in environments predisposed to desertification. The study area is the Vieira river basin, located in Montes Claros (MG, Brazil). Land use/land cover prognosis was performed for the year 2005 so that this result could be compared with the ranked image for the same year, taken as ground truth. Kappa indices were used to evaluate the change level that occurred between these two cases. Results from cellular automata were evaluated from those of the Markov chain model. The latter proved to be efficient in the quantitative prediction of changes in land use/land cover. Regarding the cellular automata, an average performance was noted in the spatial distribution of classes. Specifically, with regard to desertification, the use of the CA-Markov model was effective at estimating the total area of the most susceptible class to this process, Bare Soil; however, it was inefficient in its spatialization. Even with the caveats related to the performance of cellular automata, the overall prediction capacity of CA-Markov models can be considered as good.

Keywords: Cellular automata; Degradation; Landscape; Markov chain; Prognosis; Semiarid.