No abstract

Sustainable urban planning and management require reliable land change models, which can be used to improve decision making. The objective of this study was to test a random forest-cellular automata (RF-CA) model, which combines random forest (RF) and cellular automata (CA) models. The Kappa simulation (KSimulation), figure of merit, and components of agreement and disagreement statistics were used to validate the RF-CA model. Furthermore, the RF-CA model was compared with support vector machine cellular automata (SVM-CA) and logistic regression cellular automata (LR-CA) models. Results show that the RF-CA model outperformed the SVM-CA and LR-CA models. The RF-CA model had a Kappa simulation (KSimulation) accuracy of 0.51 (with a figure of merit statistic of 47%), while SVM-CA and LR-CA models had a KSimulation accuracy of 0.39 and −0.22 (with figure of merit statistics of 39% and 6%), respectively. Generally, the RF-CA model was relatively accurate at allocating "non-built-up to built-up" changes as reflected by the correct "non-built-up to built-up" components of agreement of 15%. The performance of the RF-CA model was attributed to the relatively accurate RF transition potential maps. Therefore, this study highlights the potential of the RF-CA model for simulating urban growth.

Rapid land use/cover change and landscape fragmentation is occurring in many countries in central and southern Africa, as a result of colonial imbalances in land distribution, demographic pressure, agricultural expansion, government policies and environmental factors such as drought. This study analysed the dynamics of land use/cover and land degradation as revealed in landscape fragmentation in the Bindura District of Zimbabwe based on Landsat data for 1973 and 2000. A hybrid supervised/ unsupervised classification approach coupled with GIS analyses was employed to generate land use/cover maps from which various class level landscape metrics were calculated using FRAGSTATS 1 , in order to analyse landscape fragmentation. The results show that agriculture, mixed rangeland, settlements, bareland and water increased, while woodland areas decreased. Consequently, the landscape became more highly fragmented as indicated by an increase in the patch number and a decrease in the mean patch size (MPS) of the woodland and mixed rangeland classes. This suggests that anthropogenic activities driven by agricultural expansion were the main causes of landscape fragmentation, leading to landscape degradation in the study area.

No abstract

No abstract