The global pandemic of COVID-19 has been influencing people’s lives and the cities. Not only people’s physical and mental health have been threatened, but also the city operation has been profoundly affected from different perspectives (e.g., social and economic) permanently. How cities can efficiently react and response to improve city resilience is an urgent issue to be addressed. The healthcare system as a vital part of the city systems is confronting intense pressure and many challenges under this emergent public health crisis of COVID-19, which might cause huge impacts on the whole city’s operation. Also, human beings as the direct victims of this public health crisis, their behaviour changes impacts on the healthcare system and the city could have been inevitable but have been neglected. In this context, this paper intends to study the citizen healthcare accessing behaviours changes in the post-pandemic era, and to unearth their impacts on the healthcare system and the city operation. For this purpose, first, a framework of influential factors for healthcare accessing was established based on a bidirectional “capability, opportunity, motivation, and behaviour” (COM-B) model and the comprehensive literature review. In which, 43 factors that would influence citizen healthcare accessing behaviour were identified and classified. Thus, based on the proposed framework, two cases (i.e., UK and China) were analysed in depth and compared based on a questionnaire survey to evaluate the factor importance and relationships under different scenarios. And the most influential factors based on analysis results are classified into 12 aspects (e.g., healthcare capability, policy support, information updating etc.). Further, a novel behaviour-healthcare system-city model based on the COM-B model was developed to rethink and indicate the relationships among citizen behaviour, healthcare system and city operation. The research results can be used by policymakers and researchers to improve the city resilience by enabling immediate responses to city systems and citizens behaviours confronting city emergencies.

Urban analytics increasingly relies on AI-driven trajectory analysis, yet current approaches suffer from methodological fragmentation: trajectory learning captures movement patterns but ignores spatial context, while spatial embedding methods encode street networks but miss temporal dynamics. Three gaps persist: (1) lack of joint training that integrates spatial and temporal representations, (2) origin-agnostic treatment that ignores directional asymmetries in navigation ($A \to B \ne B \to A$), and (3) over-reliance on auxiliary data (POIs, imagery) rather than fundamental geometric properties of urban space. We introduce a conditional trajectory encoder that jointly learns spatial and movement representations while preserving origin-dependent asymmetries using geometric features. This framework decomposes urban navigation into shared cognitive patterns and origin-specific spatial narratives, enabling quantitative measurement of cognitive asymmetries across starting locations. Our bidirectional LSTM processes visibility ratio and curvature features conditioned on learnable origin embeddings, decomposing representations into shared urban patterns and origin-specific signatures through contrastive learning. Results from six synthetic cities and real-world validation on Beijing's Xicheng District demonstrate that urban morphology creates systematic cognitive inequalities. This provides urban planners quantitative tools for assessing experiential equity, offers architects insights into layout decisions' cognitive impacts, and enables origin-aware analytics for navigation systems.

Urban transportation systems face increasing resilience challenges from extreme weather events, but current assessment methods rely on surface-level recovery indicators that miss hidden structural damage. Existing approaches cannot distinguish between true recovery and "false recovery," where traffic metrics normalize, but the underlying system dynamics permanently degrade. To address this, a new physics-constrained Hamiltonian learning algorithm combining "structural irreversibility detection" and "energy landscape reconstruction" has been developed. Our approach extracts low-dimensional state representations, identifies quasi-Hamiltonian structures through physics-constrained optimization, and quantifies structural changes via energy landscape comparison. Analysis of London's extreme rainfall in 2021 demonstrates that while surface indicators were fully recovered, our algorithm detected 64.8\% structural damage missed by traditional monitoring. Our framework provides tools for proactive structural risk assessment, enabling infrastructure investments based on true system health rather than misleading surface metrics.

Extreme weather events increasingly challenge urban transportation systems, requiring advanced methods to understand and predict traffic adaptations. Traditional graph-based approaches to traffic analysis, while effective for static conditions, struggle to capture the continuous and dynamic nature of flow patterns during weather disruptions. Current methods lack the mathematical framework to bridge discrete network structures with continuous flow dynamics, particularly in analyzing how traffic patterns reorganize under stress. This paper presents a novel field-theoretic framework for analyzing traffic flow patterns, integrating Hodge decomposition with continuous field visualization. The framework decomposes traffic flows into three fundamental components: gradient flows representing direct movements, curl flows capturing circulation patterns, and harmonic flows revealing background patterns. By transforming discrete network measurements into continuous fields, our method enables comprehensive analysis of flow pattern evolution under varying conditions. Through both synthetic experiments and a case study of London's central district during rainfall events, we demonstrate our framework's ability to reveal previously unobservable traffic adaptation patterns. The method successfully captures the emergence of alternative routes, identifies critical adaptation zones, and quantifies systematic changes in flow organization. This approach provides valuable insights for urban planners and traffic managers, offering a mathematical foundation for understanding network adaptation mechanisms and informing resilience planning strategies.