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.
The rapid development of urban retail companies brings new opportunities to the Chinese economy. Due to the spatiotemporal heterogeneity of different cities, selecting a business location in a new area has become a challenge. The application of multi‐source geospatial data makes it possible to describe human activities and urban functional zones at fine scale. We propose a knowledge transfer‐based model named KTSR to support citywide business location selections at the land‐parcel scale. This framework can optimize customer scores and study the pattern of business location selection for chain brands. First, we extract the features of each urban land parcel and study the similarities between them. Then, singular value decomposition was used to build a knowledge‐transfer model of similar urban land parcels between different cities. The results show that: (1) compared with the actual scores, the estimated deviation of the proposed model decreased by more than 50%, and the Pearson correlation coefficient reached 0.84 or higher; (2) the decomposed features were good at quantifying and describing high‐level commercial operation information, which has a strong relationship with urban functional structures. In general, our method can work for selecting business locations and estimating sale volumes and user evaluations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.