Integrating random forest and morphological spatial pattern analysis for predicting future land surface temperature dynamics: insights from urbanizing Saudi Arabia

Abstract

In the face of rapid urbanization in Saudi Arabia, understanding the impact of landscape changes on land surface temperature (LST) is crucial for sustainable urban planning. This study assesses the influence of landscape morphology on LST and predicts future LST changes. A multi-temporal land use and land cover (LULC) analysis using random forest (RF) quantified urban expansion and its ecological impacts. Accuracy assessment using the kappa coefficient illustrated the precision of the classification techniques. Morphological Spatial Pattern Analysis (MSPA), developed in Python, analyzed the structural evolution of urban areas, vegetation and exposed rocks. Polynomial regression models established the relationship between landscape morphology and LST and predicted future temperature trends. Results for Asir show a significant improvement in accuracy of the LULC models over three decades, with overall accuracy increasing from 89.99% in 1990 to 91.72% in 2020. The bootstrapping trend analysis showed an urban expansion with a positive slope of 9.27 and a decline in water bodies with a negative slope of −0.03. The MSPA analysis reflected a significant urban expansion, with the core area growing from 45.19 km2 in 2001 to 230.33 km2 in 2021. The vegetated areas showed resilience and dynamic connectivity despite slight reduction and fragmentation. The polynomial regression predicted an increase in future average LST by 2030, with urban core areas reaching 58.47 °C, vegetated cores 42.19 °C and exposed rock cores 55.79 °C. These results highlight the link between urban expansion and LST rise and make the case for integrating green infrastructure and cooling strategies into urban development.