The role of random forest and Markov chain models in understanding metropolitan urban growth trajectory

Introduction This study delves into the spatiotemporal dynamics of land use and land cover (LULC) in a Metropolitan area over three decades (1991–2021) and extends its scope to forecast future scenarios from 2031 to 2051. The intent is to aid sustainable land management and urban planning by enabling precise predictions of urban growth, leveraging the integration of remote sensing, GIS data, and observations from Landsat satellites 5, 7, and 8. Methods The research employed a machine learning-based approach, specifically utilizing the random forest (RF) algorithm, for LULC classification. Advanced modeling techniques, including CA–Markov chains and the Land Change Modeler (LCM), were harnessed to project future LULC alterations, which facilitated the development of transition probability matrices among different LULC classes. Results The investigation uncovered significant shifts in LULC, influenced largely by socio-economic factors. Notably, vegetation cover decreased substantially from 49.21% to 25.81%, while forest cover saw an increase from 31.89% to 40.05%. Urban areas expanded significantly, from 7.55% to 25.59% of the total area, translating into an increase from 76.31 km 2 in 1991 to 258.61 km 2 in 2021. Forest area also expanded from 322.25 km 2 to 409.21 km 2 . Projections indicate a further decline in vegetation cover and an increase in built-up areas to 371.44 km 2 by 2051, with a decrease in forest cover compared to its 2021 levels. The predictive accuracy of the model was confirmed with an overall accuracy exceeding 90% and a kappa coefficient around 0.88. Discussion The findings underscore the model’s reliability and provide a significant theoretical framework that integrates socio-economic development with environmental conservation. The results emphasize the need for a balanced approach towards urban growth in the Islamabad metropolitan area, underlining the essential equilibrium between development and conservation for future urban planning and management. This study underscores the importance of using advanced predictive models in guiding sustainable urban development strategies.