Under the background of rapid urban development and continuous climate change, frequent floods around the world have caused serious economic losses and social problems, which has become the main reason for the sustainable development of cities. Flood disaster risk assessment is an important non-engineering measure in urban disaster prevention and mitigation, and scientific flood disaster risk assessment is the premise and foundation of flood disaster risk management. This paper summarizes the current situation of flood risk assessment by analyzing the international literature in recent 20 years. The mechanism of flood disaster is mainly discussed. The flood disaster assessment methods are summarized, including historical disaster statistics method, multi-criteria index system method, remote sensing and GIS (Geographic Information System) coupling method, scenario simulation evaluation method and machine learning method. Furthermore, the development status of flood risk analysis and forecasting is summarized. Finally, the development trend and direction of flood risk assessment are put forward.

In urban point cloud scenarios, due to the diversity of different feature types, it becomes a primary challenge to effectively obtain point clouds of building categories from urban point clouds. Therefore, this paper proposes the Enhanced Local Feature Aggregation Semantic Segmentation Network (ELFA-RandLA-Net) based on RandLA-Net, which enables ELFA-RandLA-Net to perceive local details more efficiently by learning geometric and semantic features of urban feature point clouds to achieve end-to-end building category point cloud acquisition. Then, after extracting a single building using clustering, this paper utilizes the RANSAC algorithm to segment the single building point cloud into planes and automatically identifies the roof point cloud planes according to the point cloud cloth simulation filtering principle. Finally, to solve the problem of building roof reconstruction failure due to the lack of roof vertical plane data, we introduce the roof vertical plane inference method to ensure the accuracy of roof topology reconstruction. The experiments on semantic segmentation and building reconstruction of Dublin data show that the IoU value of semantic segmentation of buildings for the ELFA-RandLA-Net network is improved by 9.11% compared to RandLA-Net. Meanwhile, the proposed building reconstruction method outperforms the classical PolyFit method.

The image will be contaminated by noise during the imaging process, which severely degrades the image quality. It is necessary to filter the collected image. With the increasing amount of image data, the traditional single-processor or multiprocessor computing equipment has been unable to meet the requirements of real-time data processing. In this paper, the computational model of weighted mean filtering and the characteristics of high performance computer architecture are studied. An efficient hierarchical image weighted mean filtering parallel algorithm for Open Computing Language (OpenCL) is designed and implemented, which can fully express the parallelism of the computing model. The parallel algorithm takes full account of the characteristics of image discrete convolution computing and the multi-layer logic architecture of high performance computer, deeply excavates the parallelism of the computing platform and computing model, and realizes the efficient task mapping from computing model to computing resources. The model is implemented in parallel with the two levels of work-group and work-item. The experimental results show that compared with the serial algorithm based on CPU, the parallel algorithm based on Open Multi-Processing (OpenMP) and the parallel algorithm based on Compute Unified Device Architecture (CUDA), the parallel algorithm of weighted mean filtering achieves 20.88 times, 18.52 times and 1.26 times acceleration ratio on the NVIDIA GPU computing platform based on OpenCL architecture, respectively. It realizes better computing performance and runs on different Graphic Processing Unit (GPU) computing platforms, and has good portability and scalability.

Urban waterlogging is a serious urban disaster, which brings huge losses to the social economy and environment of the city. As an important means of urban rainfall inundation analysis, numerical simulation plays an important role in promoting the risk assessment of urban waterlogging. Scientific and accurate assessment of waterlogging disaster losses is of scientific significance for the formulation of disaster prevention and mitigation measures and the guidance of post-disaster recovery and reconstruction. In this study, the SCS-CN hydrological model and GIS coupling numerical simulation method were used to simulate the inundation of urban waterlogging under four different rainfall return periods and to realize the visualization of the inundation range and waterlogging depth in Zhengzhou. At the same time, based on the numerical simulation results, the building is used as the basic assessment unit to construct a refined assessment framework for urban waterlogging risk at the street community level based on hazard, exposure, and vulnerability analysis. The refined risk assessment results have an important reference value for optimizing the working ideas of waterlogging control and providing a reference for local management departments to effectively deal with waterlogging disasters.

Identifying urban functional zones is an important task in urban planning and smart city construction. Accurately identifying urban functional zones and analyzing their spatial distribution is crucial for optimizing urban spatial layout, improving urban management and balancing human–environment interaction. However, most of the existing studies focus on the analysis of individual data sources, which have difficulty fully reflecting the complex spatial structures and functional differences in cities. To solve this problem, this paper proposes a new method of urban functional area identification which integrates multi-source data and advanced algorithms. By clustering the results of multi-factor weighted kernel density, the paper can more accurately quantify the spatial distribution characteristics of urban functional areas and better reflect the functional differences among urban areas. At the same time, this paper uses the Random Forest model to optimize the POI data and the building data to improve the classification accuracy and the generalization ability of the model. The results show that the distribution of functional areas in the Fifth Ring Road region of Beijing presents the characteristics of diversification and agglomeration: the core urban area is dominated by high-density commercial service and public service functional areas, with a high degree of functional integration; The peripheral areas are mainly residential areas and green areas, with dispersed distributions, but clear functions. The overall accuracy reaches 87%, and the model can effectively reflect the distribution and spatial characteristics of urban functional areas.