Urban Heat Mitigation through AI-Optimized Green Roof Networks in Dense Metropolitan Areas

Abstract

This study aims to develop and evaluate an artificial intelligence (AI)-optimized framework for green roof networks to mitigate urban heat in dense metropolitan areas. A qualitative approach with a case study design was employed to capture the complexity of spatial, environmental, and technological interactions, as this design enables an in-depth exploration of real-world urban dynamics. The research was conducted in the Surabaya Metropolitan Area, Indonesia, selected due to its high population density, pronounced urban heat island effects, and availability of spatial and environmental data. A total of twelve informants were purposively selected, consisting of urban planners, environmental experts, and technology specialists, based on their expertise and direct involvement in urban development and sustainability initiatives. Data were collected through semi-structured interviews, document analysis, and spatial assessment, and analyzed using thematic analysis. The findings reveal that AI-optimized green roof networks significantly enhance urban heat mitigation compared to isolated installations by improving spatial distribution and ecological connectivity. The study concludes that integrating AI with green infrastructure planning offers a more adaptive and efficient solution for urban climate challenges. It is recommended that future research incorporate real-time data integration and expand comparative studies across multiple cities.