AI-Enabled Infrastructure Planning for Newcomer Integration and Resilient Community Development in Canada

This research is grounded in a complex adaptive systems framework that conceptualizes urban environments as coupled socio–infrastructure systems shaped by dynamic interactions among immigration behavior, built environment characteristics, and climate impacts. The project integrates artificial intelligence (AI), spatiotemporal data analytics, and complex system modeling to capture these interactions and enable immigration settlement pattern characterization and prediction, infrastructure gap identification, and infrastructure intervention scenario analysis. It advances three propositions: (P1) newcomer settlement patterns can be predicted as a function of socio-demographic attributes, built environment characteristics, and environmental features; (P2) mismatches between settlement locations and infrastructure accessibility, particularly under climate-related risks, lead to measurable differences in integration outcomes; and (P3) targeted infrastructure interventions, identified through scenario-based optimization, can improve service accessibility and support newcomer integration. These propositions are operationalized through three objectives: (O1) to design data-driven spatiotemporal models to characterize and predict the evolution of newcomer settlement patterns using multi-modal data; (O2) to identify infrastructure gaps by designing a socio-informed functionality metric that captures the interaction between settlement patterns, infrastructure networks, and climate-related risks; and (O3) to design AI-driven scenario optimization models and agentic AI system to evaluate infrastructure intervention strategies and guide data-driven decisions.