论文标题
使用匿名移动性数据进行动态人群估算
Dynamic Population Estimation Using Anonymized Mobility Data
论文作者
论文摘要
空间和及时的人口分布都对流行病管理，预防灾难，城市规划等都至关重要。人类流动性数据具有在高级时空分辨率下绘制种群分布的巨大潜力。电力法模型是将移动性数据映射到人群的最受欢迎的模型。但是，他们无法在不同的空间和时间分辨率下提供一致的估计，即，每当空间或时间分区方案变化时，都必须重新校准。我们建议使用静态普查数据和匿名移动性数据提出一个贝叶斯模型，以进行动态人群估计。我们的模型在不同的空间和时间分辨率下提供了一致的人口估计。
Fine population distribution both in space and in time is crucial for epidemic management, disaster prevention,urban planning and more. Human mobility data have a great potential for mapping population distribution at a high level of spatiotemporal resolution. Power law models are the most popular ones for mapping mobility data to population. However,they fail to provide consistent estimations under different spatial and temporal resolutions, i.e. they have to be recalibrated whenever the spatial or temporal partitioning scheme changes. We propose a Bayesian model for dynamic population estimation using static census data and anonymized mobility data. Our model gives consistent population estimations under different spatial and temporal resolutions.
