Land Cover Change in the Mamminasata Metropolitan Area, Indonesia, 2005–2025 and CA-Markov Prediction for 2035
Abstract
This study examines land cover change in the Mamminasata Metropolitan Area (Makassar, Maros, Gowa, and Takalar), South Sulawesi, Indonesia, between 2005 and 2025 and projects its land cover to 2035. Landsat 5 TM and Landsat 8/9 OLI surface reflectance composites were classified into seven classes on Google Earth Engine using a Random Forest classifier trained with samples derived automatically from Dynamic World labels, followed by rule-based post-classification and temporal consistency corrections. Future land cover was simulated with a CA-Markov model that combines Markov transition quantities, a gradient boosting suitability model, and cellular automata allocation. The classified maps reached overall accuracies of 77.9% (2005), 81.6% (2015), and 84.9% (2025), and the 2025 hindcast agreed with the observed map at 87.3% (Kappa 0.82; Figure of Merit 0.13). Built-up land expanded from 38,036 ha to 60,661 ha (+59.5%), while paddy fields declined by 9,457 ha (?15.1%). Dryland farms and shrubland supplied 55.3% and paddy fields 29.0% of the new built-up land in 2015–2025, and 61% of the 2005–2025 growth occurred more than 20 km from the city centre. Under a business-as-usual trend, built-up land will reach 71,293 ha in 2035, mainly within 5–15 km of the city centre, and paddy fields will fall to 48,924 ha. The findings indicate that urban growth in Mamminasata has shifted from the core city to its agricultural periphery.
Keywords
Share and Cite
Article Metrics

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

