The Random Forest-Based Method of Fine-Resolution Population Spatialization by Using the International Space Station Nighttime Photography and Social Sensing Data
The Random Forest-Based Method of Fine-Resolution Population Spatialization by Using the International Space Station Nighttime Photography and Social Sensing Data
复制标题
利用国际空间站夜间摄影和社会感知数据的基于随机森林的精细分辨率人口空间化方法
DOI：
10.3390/rs10101650
复制
发表时间：
2018-10-01
期刊：
影响因子：
5
通讯作者：
Li, Ying
中科院分区：
文献类型：
--
作者：
Li, Kangning;Chen, Yunhao;Li, Ying
尽管高分辨率人口分布在城市规划、防灾减灾、区域经济发展和改善城市人居环境等方面具有重要意义，但传统的城市调查主要集中在利用粗分辨率夜间灯光（NTL）进行大范围人口空间化，而对高分辨率人口制图的研究较少。针对小尺度人口分布生成问题，提出了一种基于随机森林回归模型的空间化方法，对国际空间站（ISS）拍摄的2500万人口数据和社会感兴趣点（POI）数据生成的城市功能区进行空间化。主要包括三个步骤，即ISS的HSL（hue saturation lightness）变换和饱和度校正、基于兴趣点的功能区地图生成和基于随机森林模型的人口空间化。通过与WorldPop算法的比较，验证了该方法的有效性，表明该方法能够生成高分辨率的人口空间分布图。在讨论中，本文认为，在没有辅助数据的情况下，NTL不能直接用作小尺度的人口指标。RF模型的变量重要性度量证实了特征与人口之间的相关性，并进一步证明了城市功能在小规模人口制图中的表现优于LULC（土地利用和土地覆盖）。城市高度对建筑物体积的补偿作用也提高了人口分解的效果。综上所述，该方法在细分精细分辨率人口和其他城市社会经济属性方面表现出巨大的潜力。
Despite the importance of high-resolution population distribution in urban planning, disaster prevention and response, region economic development, and improvement of urban habitant environment, traditional urban investigations mainly focused on large-scale population spatialization by using coarse-resolution nighttime light (NTL) while few efforts were made to fine-resolution population mapping. To address problems of generating small-scale population distribution, this paper proposed a method based on the Random Forest Regression model to spatialize a 25 m population from the International Space Station (ISS) photography and urban function zones generated from social sensing data—point-of-interest (POI). There were three main steps, namely HSL (hue saturation lightness) transformation and saturation calibration of ISS, generating functional-zone maps based on point-of-interest, and spatializing population based on the Random Forest model. After accuracy assessments by comparing with WorldPop, the proposed method was validated as a qualified method to generate fine-resolution population spatial maps. In the discussion, this paper suggested that without help of auxiliary data, NTL cannot be directly employed as a population indicator at small scale. The Variable Importance Measure of the RF model confirmed the correlation between features and population and further demonstrated that urban functions performed better than LULC (Land Use and Land Cover) in small-scale population mapping. Urban height was also shown to improve the performance of population disaggregation due to its compensation of building volume. To sum up, this proposed method showed great potential to disaggregate fine-resolution population and other urban socio-economic attributes.