Cities are engines of economic growth and innovation. To sustain growth in urban agglomerations, local governments need strategies to address disruptions caused by climate change, resource scarcity, and social inequity. Machine learning (ML) offers a powerful way for city planners to manage, predict, and mitigate these complex challenges. While urban planning has traditionally relied on techniques based on historical data and deterministic models, the dynamic and interconnected nature of contemporary challenges demands more sophisticated and AI-augmented approaches. ML algorithms today can ingest large-scale, multisource data to generate real-time predictions and identify vulnerabilities across infrastructure, mobility, and social systems. This book examines how ML supports sustainable smart cities—cities prepared to address multiple challenges while prioritizing resident quality of life by maintaining the capacity to thrive economically and socially. It explores ways to use ML to enable smarter infrastructure and building design, from system-level networks to specific applications in construction and operations. Chapters demonstrate how ML optimizes urban mobility through improved public transportation, fleet management, and urban flow prediction. The book also examines ML applications in urban resilience, including flood risk management, air quality monitoring, and disaster response systems. Additionally, it explores innovative applications in social sustainability, such as affective computing for community well-being and equity-focused planning tools. Featuring contributions from leading experts in architecture, urban planning, engineering, computer science, and sustainability, the book showcases real-world case studies of successful ML applications in cities worldwide. The resulting volume bridges theoretical developments with practical implementations, offering technical depth and actionable insights for creating sustainable urban futures.