This award-winning poster, “Explainable AI for Urban Sustainability Trade-offs – A Singapore Case Study,” presents a Graph Neural Network (GNN) framework to analyze how urban morphology jointly influences environmental and societal performance in Singapore. By integrating spatial graph structures with explainable AI techniques, the study identifies key drivers—such as green plot ratio, building height, and density—that shape sustainability trade-offs. Using Pareto and “Super Node” analysis, the research reveals high-impact urban typologies and actionable optimization strategies. The findings provide interpretable, data-driven guidance for planners and policymakers to enhance environmental and societal outcomes and advance sustainable urban development.
