High-rise developments frequently exert adverse impacts on the outdoor wind environment, leading to a deterioration in the overall quality of urban surroundings and a reduction in the comfort levels of residents. This study systematically investigates typical high-rise settlements in Xuzhou City and proposes optimization strategies to address wind environment issues through an in-depth analysis of building planning parameters. Utilizing Computational Fluid Dynamics (CFD) simulations, the research identifies key wind-related challenges associated with high-rise buildings in representative settlements. The study comprehensively examines the effects of building height, width, orientation, spacing, and layout on the outdoor wind field, progressing from individual building units to clusters. Based on these findings, optimization strategies are formulated and validated through CFD simulations conducted on a representative high-rise settlement in Xuzhou. The results reveal that typical high-rise buildings in Xuzhou exhibit a height of 54 m, a width of 48 m, and an orientation ranging from 15° to 30° southeast. The front-to-rear building spacing is approximately 1.44 times the building height, with an additional 15 m spacing from mountain walls. Optimal wind conditions are achieved with a center-vacant building layout. The optimization of building form, spacing, and orientation substantially improves the outdoor wind environment by alleviating stagnant wind zones and reducing wind pressure differentials between the building fronts and rears, thereby enhancing the comfort of residents. This study provides a valuable reference for the planning and design of high-rise settlements, contributing to an improvement in urban environmental quality and the enhancement of livability.

China’s urban development has entered the stage of urban renewal, transitioning from large-scale incremental construction to stock enhancement and renovation. In response to challenges such as traffic congestion and land-use constraints, urban planning has increasingly prioritized the development of urban underground space (UUS) and urban rail transit (URT). However, disparities in development levels across cities, as well as the fragmented and uncoordinated integration of UUS and URT, remain significant challenges. While existing studies have predominantly examined UUS and URT independently, the interaction between the two has been largely overlooked. In order to supplement this gap, the aim of this study is to construct an integrated measurement framework and quantitatively assess the level of integration between UUS and URT in 38 Chinese cities. We seek to explore the interrelationship between the two, identify the differences in the integration process across cities, and discuss the potential implications for urban planning and policy making. Specifically, this study assembles an integration measurement index framework from three dimensions (UUS, URT, and urban development), quantitatively evaluates the integration level of 38 Chinese cities by using the entropy weighting and VIKOR methods, and summarizes the regionalization characteristics by using K-means clustering. The results of the study show that (1) there is a positive correlation between UUS development and URT construction and the degree of correlation is affected by the level of urban development; (2) the construction of URT is dominant in the integrated system of UUS and URT; (3) the sample cities can be classified according to the characteristics of the integration into the types of developing cities (47.37%), mature cities (21.05%), and underdeveloped cities (31.58%), and there is a clustering effect on the overall spatial distribution.

With the acceleration of climate change and the increase of extreme rainfall, the risk of flooding has intensified in the Huang-Huai region, which is often hit by floods. Urban water accumulation is a complicated process, and the hydrological simulation analysis is highly accurate, but it is time-consuming and laborious. Machine learning is becoming an important new method because of its ability to analyze large areas with high precision. In this paper, a simulation analysis method based on machine learning is constructed by selecting 13 disaster factors, and the waterlogging point in Xuzhou city is predicted successfully. The following conclusions are found: (1) Among the five machine learning models, CatBoost has the highest accuracy rate, reaching 81.67%. (2) Temperature, elevation, and rainfall are relatively important influencing factors of waterlogging. (3) Machine learning can discover water accumulation areas that are easily overlooked except for the built-up areas. (4) The results of the coupling analysis show that the exposure risk of the population exposed to rainwater in the old urban area, the southern area, and the northwestern area is relatively high. This research is of great significance for reducing the risk of exposure to rain and flooding and promoting the safety and sustainable development of cities.