Urban flooding, as one of the most serious natural disasters, has caused considerable personal injury and property damage throughout the world. To better cope with the problem of waterlogging, the experts have developed many waterlogging models that can accurately simulate the process of pipe network drainage and water accumulation. The study of urban waterlogging involves many data types. These data come from the departments of hydrology, meteorology, planning, surveying, and mapping, etc. The incoordination of space–time scale and format standard has brought huge obstacles to the study of urban waterlogging. This is not conducive to interpretation, transmission, and visualization in today’s network environment. In this paper, the entities and attributes related to waterlogging are defined. Based on the five modules of urban drainage network, sub basin, dynamic water body, time series, and meteorological data, the corresponding UML (Unified Modeling Language) model is designed and constructed. On this basis, the urban waterlogging application domain extension model city waterlogging application domain extension (CTWLADE) is established. According to the characteristics of different types of data, two different methods based on FME object and citygml4j are proposed to realize the corresponding data integration, and KML (Keyhole Markup Language) /glTF data organization form and the corresponding sharing method are proposed to solve the problem that the CTWLADE model data cannot be visualized directly on the web and cannot interact in three-dimensional format. To evaluate the CTWLADE, a prototype system was implemented, which can convert waterlogging-related multi-source data in extensible markup language (XML) files conform. The current CTWLADE can map the data required and provided by the hydraulic software tool storm water management model (SWMM) and is ready to be integrated into a Web 3D Service to provide the data for 3D dynamic visualization in interactive scenes.

With the acceleration of the urbanization process, the problems caused by extreme weather such as heavy rainstorm events have become more and more serious. During such events, the road and its auxiliary facilities may be damaged in the process of the rainstorm and waterlogging, resulting in the decline of its traffic capacity. Rainfall is a continuous process in a space–time dimension, and as rainfall data are obtained through discrete monitoring stations, the acquired rainfall data have discrete characteristics of time interval and space. In order to facilitate users in understanding the impact of urban waterlogging on traffic, the visualization of waterlogging information needs to be displayed under different spatial and temporal granularity. Therefore, the appropriateness of the visualization granularity directly affects the user’s cognition of the road waterlogging map. To solve this problem, this paper established a spatial granularity and temporal granularity computing quantitative model for spatio-temporal visualization of road waterlogging and the evaluation method of the model was based on the cognition experiment. The minimum visualization unit of the road section is 50 m and we proposed a 5-level depth grading method and two color schemes for road waterlogging visualization based on the user’s cognition. To verify the feasibility of the method, we developed a prototype system and implemented a dynamic spatio-temporal visualization of the waterlogging process in the main urban area of Nanjing, China. The user cognition experiment showed that most participants thought that the segmentation of road was helpful to the local visual expression of waterlogging, and the color schemes of waterlogging depth were also helpful to display the road waterlogging information more effectively.

Rapid urban population aging and increasing land constraints pose significant challenges for improving both service coverage and spatial equity in elderly care facility planning. This study develops an integrated optimization framework that simultaneously addresses accessibility, efficiency, and equity in the spatial allocation of elderly care facilities. First, an improved Gaussian Two-Step Floating Catchment Area (G2SFCA) method is employed to evaluate accessibility patterns across multiple facility types under both walking and driving scenarios. Second, resource allocation equity is quantified using Lorenz curves and spatial Gini coefficients to identify mismatches between elderly care supply and population demand. Building upon these analyses, a fairness-oriented maximum covering location model—termed the Equity Maximum Covering Location Problem (EMCLP)—is formulated and further transformed into a Markov Decision Process. A deep reinforcement learning-based algorithm is subsequently designed to solve the EMCLP under complex spatial constraints. Experiment results demonstrate that the proposed approach achieves improved computational efficiency while maintaining robust solution quality, and effectively enhances service provision in underserved areas through differentiated functional allocation strategies.