QGA Fuzzy C-Means method for Urban Heat Island Detection Using Remote Sensing Data

—In this paper, we propose a novel Urban Heat Island detection method in which a Quantum-Inspired Genetic Algorithm is executed to determine the optimal initialization of the cluster centres in Fuzzy C-Means. Our method aims to overcome limitations related to sensitivity to initial cluster centres in traditional FCM improving the accuracy of the urban heat islands detected. The method is implemented in a GIS based framework and was tested using Landsat 8-derived Land Surface Temperature and Normalized Difference Vegetation Index data for the city of Naples, Italy. Experimental results show that the proposed method leads to higher clustering accuracy and better identification of critical urban heat zones compared to classical approaches. The results highlight the potential of Quantum Inspired algorithms as practical tools for enhancing environmental data analysis and supporting urban climate resilience strategies.