Case Studies in Chemical and Environmental Engineering (Jun 2023)
Simulating and predicting future land-use/land cover trends using CA- Markov and LCM models
Abstract
In recent years, several factors have influenced the evolution of land use, and this rapid evolution presents major challenges to decision makers and researchers in terms of sustainable land management and planning. Modeling and projecting future trends in land use change has become a must as a tool for decision making. This study aims to use data and satellite images of the Lakhdar-Morocco sub-basin over a period of 20 years, in order to make predictions of future trends for the year 2019-2039 using and comparing the two models CA-MARKOV and LCM. The images used are Landsat 5-TM and Landsat 8-OLI for the years 2000, 2007, 2010, 2019. The classification used is the supervised method by maximum Likelihood, this method helps us identifying four categories of land use: water body, forest, vegetation, bareland with urban area. The validation of the results of the predictions and the determination of the accuracy of the models, was determined by the kappa index and the confusion matrix. A good to perfect level of agreement was observed by the CA-Markov model for the two test years: 2010 (Kstandard = 0.86 and Klocation = 0.88), and 2019 (Kstandard = 0.76 and Klocation = 0.80). The results indicate that the major changes will affect the forest area which will undergo decreases in the coming years and will be affected by urbanization where we will have a decrease in forest areas of 70% from 2000 to 2039 and in parallel an increase of about 37% of bare land and urban area. This increase in urban uses is due to the impact of the constant increase in economic and demographic development, and on the other hand the water body will remain constant with changes in the vegetation cover. These results indicate the need to create new strategies in the area to protect the sustainability of land uses in the Lakhdar sub-basin and protect the vegetation cover and forests from deforestation and erosion.
