No abstract

The development of geospatial big data makes it possible to study traffic-congestion issues. In particular, floating car data (FCD) is very suitable for it because FCD can help predict traffic-congestion bottlenecks and provide corresponding solutions to address traffic problems. Previous studies have discussed the impacts of rainfall on road speeds, but few studies have focused on the impacts of rainfall on the spatial distribution and changes in traffic-congestion bottlenecks throughout a mega-city. This article proposes an index calculation and clustering (ICC) model by integrating PageRank and clustering algorithms from multisource data, including rainfall data, FCD, and OpenStreetMap data. As the study area, we selected Shenzhen, which is the largest developed city in South China. The results demonstrate three peak periods of citizen travel, namely, 8:00-10:00, 14:00-16:00, and 18:00-20:00. Road speeds after rainfall decrease by 6.20% on weekdays and by 2.37% on weekends, and traffic-congestion areas increase by 23.53% and 20.65% on weekdays and on weekends, respectively. In addition, rainfall causes more significant effects on traffic conditions on weekdays compared with on weekends in Shenzhen. Compared with a traditional kernel density analysis, the proposed ICC model can offer a more thorough understanding of urban traffic-congestion areas, which can help policy makers optimize alleviation strategies.

No abstract

e spatial distribution pattern of jobs and housing plays a vital role in urban planning and traffic construction. However, obtaining the jobs-housing distribution at a fine scale (e.g., the perspective of individual jobs-housing attribute) presents difficulties due to a lack of social media data and useful models. With user data acquired from a location-based service provider in China, this study employs a deep bag-of-features network (BagNet) to classify remote-sensing (RS) images into various jobshousing types. Considering Wuhan, one of the fastest developing cities in China, as a case study area, three jobs-housing types (i.e., only working, only living, and both working and living) at the land-parcel level are obtained. We demonstrate that the multiscale random sampling method can reduce the influence of image noise, increase the utilization of training data, and reduce network overfitting. By altering the network structure and the training strategy, BagNet achieved excellent fitting accuracy for identifying each jobs-housing type (overall accuracy > 0.84 and kappa > 0.8). For the first time, we demonstrate that urban socioeconomic characteristics can be obtained from high-resolution RS images using deep learning techniques. Additionally, we conclude that the total level of mixing within Wuhan is not high at present; however, Wuhan is continuously improving the mixture of jobs and housing. is study has reference value for extracting urban socioeconomic characteristics from RS images and could be used in urban planning as well as government management.