Exploring the impact of AI on public open and green space planning to optimize urban sustainability

Abstract Urban sustainability is increasingly challenged by rapid urbanization, environmental degradation, and unequal access to public open and green spaces. These spaces are essential for mitigating urban heat, enhancing biodiversity, and improving human well-being. However, planning and managing them equitably in dense cities remains a complex task. This study explores how artificial intelligence (AI) can enhance the planning, design, and management of green spaces to optimize urban sustainability. Drawing upon recent advances in machine learning, deep learning, and geospatial intelligence, the research synthesizes literature and case studies that demonstrate AI’s potential to improve data-driven decision-making, spatial optimization, and predictive environmental modeling. Integrating AI with Geographic Information Systems (GIS) and multi-criteria decision-making frameworks enables planners to identify underserved areas, forecast future demands, and evaluate the ecological and social performance of green infrastructure. Emerging approaches such as GeoAI and neural network models (e.g., CNNs, LSTMs) support dynamic and adaptive green space allocation that enhances accessibility, resilience, and inclusivity. Despite significant progress, challenges persist regarding data quality, interoperability, ethical transparency, and policy integration. By assessing these opportunities and constraints, this research develops a conceptual framework for embedding AI technologies into sustainable urban planning practices. The findings underscore that AI, when responsibly implemented, can transform POGS into intelligent, adaptive systems that align with equity, ecological health, and long-term urban resilience goals.