Understanding the spatiotemporal dynamics of urban population is crucial for addressing a wide range of urban planning and management issues. Aggregated geospatial big data have been widely used to quantitatively estimate population distribution at fine spatial scales over a given time period. However, it is still a challenge to estimate population density at a fine temporal resolution over a large geographical space, mainly due to the temporal asynchrony of population movement and the challenges to acquiring a complete individual movement record. In this article, we propose a method to estimate hourly population density by examining the time‐series individual trajectories, which were reconstructed from call detail records using BP neural networks. We first used BP neural networks to predict the positions of mobile phone users at an hourly interval and then estimated the hourly population density using log‐linear regression at the cell tower level. The estimated population density is linearly correlated with population census data at the sub‐district level. Trajectory clustering results show five distinct diurnal dynamic patterns of population movement in the study area, revealing spatially explicit characteristics of the diurnal commuting flows, though the driving forces of the flows need further investigation. 相似文献
Geotechnical and Geological Engineering - In order to reveal the mechanism of surrounding rock deformation and instability of soft rock roadway in 12# working face of Puhe coal mine, and... 相似文献
Identifying and analyzing the urban–rural differences of social vulnerability to natural hazards is imperative to ensure that urbanization develops in a way that lessens the impacts of disasters and generate building resilient livelihoods in China. Using data from the 2000 and 2010 population censuses, this study conducted an assessment of the social vulnerability index (SVI) by applying the projection pursuit cluster model. The temporal and spatial changes of social vulnerability in urban and rural areas were then examined during China’s rapid urbanization period. An index of urban–rural differences in social vulnerability (SVID) was derived, and the global and local Moran’s I of the SVID were calculated to assess the spatial variation and association between the urban and rural SVI. In order to fully determine the impacts of urbanization in relation to social vulnerability, a spatial autoregressive model and Bivariate Moran’s I between urbanization and SVI were both calculated. The urban and rural SVI both displayed a steadily decreasing trend from 2000 to 2010, although the urban SVI was always larger than the rural SVI in the same year. In 17.5% of the prefectures, the rural SVI was larger than the urban SVI in 2000, but was smaller than the urban SVI in 2010. About 12.6% of the urban areas in the prefectures became less vulnerable than rural areas over the study period, while in more than 51.73% of the prefectures the urban–rural SVI gap decreased over the same period. The SVID values in all prefectures had a significantly positive spatial autocorrelation and spatial clusters were apparent. Over time, social vulnerability to natural hazards at the prefecture-level displayed a gathering–scattering pattern across China. Though a regional variation of social vulnerability developed during China’s rapid urbanization, the overall trend was for a steady reduction in social vulnerability in both urban and rural areas.