Semi-Markov Modeling in Discrete Time and State for the Study of Desertification in Nigeria

Abstract

The area of land lost to desert encroachment in a year in Nigeria has been considered as a stochastic process. A semi-Markov and gap size model has been utilized to study the process. The model defines a discrete-time, discrete-state process in which successive state occupancies are governed by the transition probabilities of the Markov process. The model was tested by examining the historical data for the desertification in Nigeria. The result indicates a slow and continuous loss of Nigeria cropland of about 1.4% to desert in 200 years. The result could be useful to the government and non-governmental organizations for the control of desert in Nigeria.