Geospatial modeling offers critical insights for assessing emergency shelter accessibility in the context of disaster-induced disruptions in flood-prone cities. This study develops a GIS-based framework that integrates hydrodynamic flood simulation and accessibility analysis to evaluate flood-induced road disruptions in central Guangzhou, China. Using the Cellular Automata Dual-DraInagE Simulation (CADDIES)-2D model, flooding scenarios with 10-, 20-, and 50-year return periods were simulated, and impassable roads were incorporated into a network-based analysis. Community-level accessibility to shelters was measured with the Gaussian Two-Step Floating Catchment Area (G2SFCA) method, which accounts for shelter capacity, distance decay, and disrupted travel paths. Results show a progressive decline in accessibility as flood severity increases: 46.77%, 47.44%, and 52.56% of communities experienced reduced access under the three scenarios. The number of high-risk communities, those exposed to both severe flooding and high vulnerability (measured by accessibility and socioeconomic conditions), rose from 6 (10-year) to 34 (20-year) and 98 (50-year). These communities are mainly concentrated in peripheral districts with sparse shelter coverage. These findings underscore the need for spatially optimized shelter allocation, resilient evacuation routes, and consideration of social vulnerability in emergency planning. The proposed framework offers transferable insights for urban resilience strategies, supporting equitable disaster preparedness in other flood-prone megacities.

Obtaining information about various vehicle types traveling on road networks is crucial for estimating traffic loads on roads, evaluating the adequacy of road design standards, and providing personalized navigation guidance. Traditional intrusive and non-intrusive methods for vehicle-type identification often encounter challenges such as high maintenance costs, incomplete coverage of all roads, and technical limitations in adverse weather conditions. In recent years, vehicle GNSS trajectory data accumulation has provided a continuous, dynamic, wide-coverage, and cost-effective data resource for identifying vehicle types. However, existing trajectory-based methods still have some drawbacks in micro-trip segmentation and limitation of movement features. Hence, this paper proposes a novel approach for identifying vehicle types by leveraging spatial-semantic information from trajectory data. This proposed method initially detects staying points from trajectory data, then utilizes DBSCAN clustering on these detected staying points to adaptively segment original vehicle trajectories into various micro-trips in a steady-moving pattern. Subsequently, several statistical indicators related to velocity and acceleration are calculated as movement features for each micro-trip. Additionally, each vehicle trajectory’s driving-road hierarchy and staying-place information are quantified as the geo-semantic features. Finally, the calculated movement and geo-semantic features are utilized for two classification tasks using three typical classification models. Experimental results demonstrate that the proposed method achieves reliable performance in identifying various vehicle types by incorporating adaptive micro-trip segmentation and multiple spatial-semantic features, particularly outperforming fixed-size trip segmentation and using only movement features. Furthermore, it is observed that the classification accuracy of coaches, trucks, and semis is consistently higher than that for large, medium, and small passenger cars, indicating that the vehicle purposes may be more distinguishable than vehicle loads.