Optimization of Landscape Activity Space in Smart City Cultural Blocks using Spatiotemporal Data Mining and NSGA-II Multi-Objective Genetic Algorithm

In the context of smart city development, the optimization of landscape activity spaces in cultural blocks is crucial for enhancing urban living. This study employs spatiotemporal data mining and the NSGA-II multi-objective genetic algorithm to address issues such as inefficient spatial utilization and poor functional zoning in traditional landscape designs. By installing flow monitoring sensors and utilizing mobile data analytics, detailed pedestrian flow and activity hotspots within Nanjing s Confucius Temple area were analyzed, leading to a balanced and efficient spatial layout proposal. Results show significant improvements: the standard deviation of pedestrian flow distribution decreased from 15.14 to 3.03, demonstrating a more balanced human traffic flow. Moreover, the average utilization rate of activity spaces increased from 0.73 to 0.93, indicating enhanced spatial utility. These findings suggest that integrating spatiotemporal data mining with multi-objective optimization algorithms can substantially refine the functional and aesthetic qualities of urban cultural districts, offering a replicable model for smart city developments worldwide.