Future cities imagined by ChatGPT-4o: human evaluation using importance-performance analysis

Despite the growing integration of artificial intelligence (AI) into human society, a significant gap remains in understanding how AI can use its database-driven imagination to enhance urban planning and aesthetics effectively. This study explores ChatGPT-4o’s potential in generating future urban designs by incorporating human evaluations. Using a mixed-methods design, the study identified key indicators for evaluating AI-generated urban design images and then applied Importance-Performance Analysis (IPA) to measure participants’ evaluations of these indicators. Results showed that creativity was the most critical indicator needing improvement, while technological sense received high performance. Surprisingly, indicators like traffic rationality, environmental greening, public space utilization and cultural representation were deemed less important. These findings suggest that participants prefer AI to focus more on bold, imaginative aspects. This study constructs a framework for evaluating AI-generated urban design images and offers valuable insights for improving AI applications in urban planning and image generation.