A Survey of Physics-Informed AI for Complex Urban Systems
🤖 AI Summary
This study addresses the challenges of low predictive accuracy, poor interpretability, and insufficient decision support in modeling complex urban systems. To this end, we propose a systematic Physics-Informed Artificial Intelligence (Physics-Informed AI) framework. We introduce a novel three-tier integration paradigm: “Physics-Integrated AI,” “Physics-AI Hybrid Ensemble,” and “AI-Integrated Physics.” The framework establishes a taxonomy of seven methodological classes spanning eight urban domains—including energy, transportation, and emergency management—and incorporates key techniques such as PDE-constrained learning, physics-based loss functions, multi-fidelity modeling, hybrid surrogate models, and knowledge-embedded neural networks. We explicitly characterize applicability scopes and data requirements for each method and identify critical research gaps. This work provides both theoretical foundations and practical pathways toward next-generation smart city modeling that is interpretable, highly reliable, and adaptive.
Application Category
📝 Abstract
Urban systems are typical examples of complex systems, where the integration of physics-based modeling with artificial intelligence (AI) presents a promising paradigm for enhancing predictive accuracy, interpretability, and decision-making. In this context, AI excels at capturing complex, nonlinear relationships, while physics-based models ensure consistency with real-world laws and provide interpretable insights. We provide a comprehensive review of physics-informed AI methods in urban applications. The proposed taxonomy categorizes existing approaches into three paradigms - Physics-Integrated AI, Physics-AI Hybrid Ensemble, and AI-Integrated Physics - and further details seven representative methods. This classification clarifies the varying degrees and directions of physics-AI integration, guiding the selection and development of appropriate methods based on application needs and data availability. We systematically examine their applications across eight key urban domains: energy, environment, economy, transportation, information, public services, emergency management, and the urban system as a whole. Our analysis highlights how these methodologies leverage physical laws and data-driven models to address urban challenges, enhancing system reliability, efficiency, and adaptability. By synthesizing existing methodologies and their urban applications, we identify critical gaps and outline future research directions, paving the way toward next-generation intelligent urban system modeling.
Problem
Research questions and friction points this paper is trying to address.
Integrating physics and AI for urban system modeling
Classifying physics-AI methods for urban applications
Addressing urban challenges via physics-informed AI
Innovation
Methods, ideas, or system contributions that make the work stand out.
Physics-Integrated AI enhances urban predictive accuracy
Physics-AI Hybrid Ensemble combines models for interpretability
AI-Integrated Physics leverages data-driven urban solutions
🔎 Similar Papers
No similar papers found.
