A Comparative Evaluation of CA-Markov and Random Forest-Cellular Automata Models for Predicting Urban Sprawl in Dar es Salaam, Tanzania
DOI:
https://doi.org/10.56279/jgat.v46i2.389Abstract
Urban expansion in rapidly growing African cities requires accurate predictive tools to guide sustainable urban planning. This study compared the performance of two spatial modelling approaches, Cellular Automata-Markov Chain (CA-Markov) and Random Forest-Cellular Automata (RF-CA), in forecasting urban sprawl in Dar es Salaam, Tanzania. Multitemporal Landsat imagery (1995, 2004, 2014, and 2024) and key biophysical and socioeconomic drivers were used to model past dynamics and predict the 2024 urban extent. The Random Forest–Cellular Automata (RF-CA) model integrated machine-learning-derived transition probabilities with a neighborhood-based CA framework, whereas the CA-Markov model relied on historical transition probabilities calibrated from previous time steps. The results showed that RF-CA achieved a higher predictive performance (accuracy: 77.84%; Kappa: 0.67; Figure of Merit (FoM): 56.83%) than CA-Markov (accuracy: 69.38%; Kappa: 0.542; Figure of Merit (FoM): 51.33%) and more accurately captured the spatial complexity in peri-urban areas. Population density, elevation, and climate were the most influential predictors. These findings highlight the value of hybrid machine learning models for urban growth prediction in rapidly transforming cities, and demonstrate their advantages over traditional Markov-based models. Furthermore, this study advances geographic information systems and remote sensing (GIS and RS) by providing empirical evidence of RF-CA's efficacy of RF-CA in data-scarce African settings.