This book introduces the paradigm of "building with data", where spatial intelligence, urban morphology, climate resilience, and infrastructure optimization are harmonized through AI-driven simulations. Machine learning models, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Proximal Policy Optimization (PPO), are leveraged to simulate urban expansion, optimize land use, and refine classification policies. These hybrid frameworks integrate spatial classification with reinforcement learning, enabling cities to proactively adapt to developmental pressures while maintaining ecological balance and ensuring socioeconomic fairness.
This book introduces the paradigm of "building with data", where spatial intelligence, urban morphology, climate resilience, and infrastructure optimization are harmonized through AI-driven simulations. Machine learning models, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Proximal Policy Optimization (PPO), are leveraged to simulate urban expansion, optimize land use, and refine classification policies. These hybrid frameworks integrate spatial classification with reinforcement learning, enabling cities to proactively adapt to developmental pressures while maintaining ecological balance and ensuring socioeconomic fairness.
Dimitrios Sargiotis
Artificial Intelligence in urban sustainability Spatio-Temporal Graph Networks smart city AI in resource optimization machine learning for urban resilience decentralized AI systems Artificial Intelligence in urban planning AI-driven smart cities data-driven urban development digital twins in cities reinforcement learning for traffic optimization AI-Enhanced Urban Planning Digital Twins Predictive Urban Modeling Graph Spatio-Demographic Neural Networks (GSDNN)