Quantitative Analysis of Urban Heat Island and ISA Density Effects on Land Surface Temperature: A Remote Sensing Study Using Local Morphological Density Analysis and Hybrid Optimization Model

Urban Heat Island (UHI) phenomenon, driven by rapid urbanization and increased Impervious Surface Areas (ISA) density, is a significant challenge to sustainable urban development and climate resilience. A robust understanding of the relationship between ISA density and Land Surface Temperature (LST) is critical for mitigating UHI effects. A key component in UHI analysis is the accurate extraction of UHI zones, which depends on the chosen threshold values. Traditional approaches often rely on static methods to identify UHI thresholds and simple regression models, which may not fully capture the complex, nonlinear interactions between ISA density and LST. Therefore, this study introduces a hybrid optimization model that integrates Genetic Algorithm-Simulated Annealing with Generalized Additive Models to assess the impact of ISA density on LST and thus define UHI thresholds. The model is applied to Algiers (2012-2021) and Taranto (2000-2014) cities using ASTER data. A local morphological density analysis was employed to quantify ISA and green space densities. Findings reveal a distinct positive nonlinear relationship between the ISA density and LST, identifying critical thresholds beyond which temperature escalates sharply. UHI zones exhibited significantly higher mean LST values, reaching 42.11°C in Taranto and 38.38°C in Algiers. Moreover, green space density was found to mitigate LST, reinforcing the pivotal role of vegetation in urban climate regulation. The findings of this adaptive modeling framework highlight the necessity of sustainable urban planning and the potential of data-driven approaches for refining climate adaptation strategies.