Generative Adversarial Networks for Climate-Sensitive Urban Morphology: An Integration of Pix2Pix and the Cycle Generative Adversarial Network

Urban heat island (UHI) effects pose significant challenges to sustainable urban development, necessitating innovative modeling techniques to optimize urban morphology for thermal resilience. This study integrates the Pix2Pix and CycleGAN architectures to generate high-fidelity urban morphology models aligned with local climate zones (LCZs), enhancing their applicability to urban climate studies. This research focuses on eight major Chinese coastal cities, leveraging a robust dataset of 4712 samples to train the generative models. Quantitative evaluations demonstrated that the integration of CycleGAN with Pix2Pix substantially improved structural fidelity and realism in urban morphology synthesis, achieving a peak Structural Similarity Index Measure (SSIM) of 0.918 and a coefficient of determination (R 2 ) of 0.987. The total adversarial loss in Pix2Pix training stabilized at 0.19 after 811 iterations, ensuring high convergence in urban structure generation. Additionally, CycleGAN-enhanced outputs exhibited a 35% reduction in relative error compared to Pix2Pix-generated images, significantly improving edge preservation and urban feature accuracy. By incorporating LCZ data, the proposed framework successfully bridges urban morphology modeling with climate-responsive urban planning, enabling adaptive design strategies for mitigating UHI effects. This study integrates Pix2Pix and CycleGAN architectures to enhance the realism and structural fidelity of urban morphology generation, while incorporating the LCZ classification framework to produce urban forms that align with specific climatological conditions. Compared to the model trained by Pix2Pix coupled with LCZ alone, the approach offers urban planners a more precise tool for designing climate-responsive cities, optimizing urban layouts to mitigate heat island effects, improve energy efficiency, and enhance resilience.