In the context of increasing frequency and impact of flood events, traditional methods for estimating flood depth have become insufficient to meet current demands, leading to a gradual shift toward machine learning approaches. This article reviews, for the first time, the applications of machine learning models—including both single and hybrid models—in flood depth estimation, referencing 108 relevant studies. Through statistical analysis, this research explored the most commonly used machine learning models and their primary data sources. Building on this foundation, we also examined the potential for integrating machine learning methods with smart city frameworks and artificial intelligence large models for flood depth calculations. The findings indicate that machine learning models excel in handling large-scale complex data and nonlinear relationships, and their performance can be further optimized through combinations with various models, significantly enhancing the accuracy and efficiency of flood depth estimation. However, these models also face challenges such as data dependency, model interpretability, and transferability. This review reveals the potential of applying machine learning models in flood depth estimation, providing directions for future research and reliable support for disaster prevention and reduction efforts.

In June 4, 2020, Corona Virus Disease 2019(COVID-19) cases in Wuhan were cleared, and the epidemic situation was basically controlled. Such public safety infectious disease includes influences great pressure on the national economy. At present, some countries and regions in the world are still in epidemic situation, and there is an urgent need to judge the infection situation and travel risk in the region. In a relatively fine scale down to perceive the surrounding situation, and then rational zoning decisions to promote the resumption of production and work. In this study, indicators for the evaluation of COVID-19 epidemic were constructed using multi-sourced data. A computational evaluation of 736 fine-grained grids was performed using the GeoDetector model and the decision tree model. The study found that the risk level in older neighborhoods was much higher than in newer neighborhoods; the population density was the most important determinant of infection; the number of urban people slumped to 37% of that in usual times according to Tencent data after the “city closure”; The model this paper used portrays the major factor in defining low-risk areas and high-risk areas, and offers suggestions and assessment from a geographical perspective to fight COVID-19, thus presenting great practical value.

Accurate risk assessment is essential to help allocate the resource for disaster relief and make the evacuation decision when hit by a Tropical Cyclone (TC). The integrated analysis of the hazard-bearing body and the intrinsic characteristics of TCs are promising to provide a clear pattern of the caused risks. However, in the literature, the origin of a TC is not considered in risk assessment. In this article, we propose a risk assessment method aided the analysis of the origins of TCs. Specifically, in order to obtain the knowledge of potential risk, this method first clustered the origins of TCs by an improved ST-DBSCAN algorithm and then make an integrated analysis by combining the analysis results with the hazard-bearing body. A case study is performed to verify the performance of the proposed method. In the study, 1760 TCs generated in the Western North Pacific from 1949 to 2016 are investigated. Results show that the improved ST-DBSCAN can identify regions where TCs generated there have stronger intensities and are more likely to make landfall, and the provincial risks are distinct among TCs generated from different areas. Analysis of annual risk changes in provinces is performed based on the results. These results are valuable for both TC disaster prevention and mitigation.

The urban structure is the spatial reflection of various economic and cultural factors acting on the urban territory. Different from the physical structure, urban structure is closely related to the population mobility. Taxi trajectories are widely distributed, completely spontaneous, closely related to travel needs, and massive in data volume. Mining it not only can help us better understand the flow pattern of a city, but also provides a new perspective for interpreting the urban structure. On the basis of massive taxi trajectory data in Chengdu, we introduce a network science approach to analysis, propose a new framework for interaction analysis, and model the intrinsic connections within cities. The spatial grid of fine particles and the trajectory connections between them are used to resolve the urban structure. The results show that: (1) Based on 200,000 taxi trajectories, we constructed a spatial network of traffic flow using the interaction analysis framework and extracted the cold hot spots among them. (2) We divide the 400 traffic flow network nodes into 6 communities. Community 2 has high centrality and density, and belongs to the core built-up area of the city. (3) A traffic direction field is proposed to describe the direction of the traffic flow network, and the direction of traffic flow roughly presents an inflow from northeast to southwest and an outflow from southeast to northwest of the study area. The interaction analysis framework proposed in this study can be applied to other cities or other research areas (e.g., population migration), and it could extract the directional nature of the network as well as the hierarchical structure of the city.

The current application of highway toll system generally uses the Dijkstra algorithm to calculate the shortest path of vehicles from the entrance to the exit to charge. This means that managers have no way of knowing the exact route of vehicles. Also, different routes of highways are often funded and operated by different investors. To address this problem, this article presents a new algorithm to reconstruct trajectories from sparse and noisy fingerprint signals from communication base stations identifications (CBSIDs), with practical application in a high-speed toll collection system in Hubei Province, China. In this solution, we use an inexpensive device that collects signal fingerprint identification numbers from CBSIDs at a low sampling rate. These CBSIDs are then matched with a special CBSID-anchor radiomap, converting the sequence of CBSIDs into a sequence of candidate anchors (toll stations and intersections on highways). Finally, a route mapping algorithm is run to process these candidate anchors and to generate the complete driving route. In the experiment on both simulated and field routes, results show that the proposed algorithm can effectively reconstruct the driving routes of vehicles. The upgraded toll collection system meets the needs of efficient motorway investment, maintenance, and management.