顾及格网属性分级与空间关联的人口空间化方法

Population Spatialization by Considering Pixel‑Level Attribute Grading and Spatial Association

现有人口空间化方法多基于行政单元构建回归模型并分配格网单元人口,但分析单元的尺度差异引发模型迁移问题。同时,格网特征建模仅考虑格网自身属性,导致格网间空间关联被人为割裂。为此,基于随机森林模型提出一种顾及格网属性分级与空间关联的人口空间化方法。该方法在格网特征建模中:(1)基于自然断点法构造建筑区类别约束的夜间灯光分级特征,并在行政单元尺度统计各等级网格占比作为训练输入,以减小模型跨尺度误差;(2)利用核密度估计刻画邻域兴趣点(point of interest,POI)对当前格网人口分布的影响及距离衰减效应;(3)基于叠置分析统计不同类型建筑区轮廓包含的各类POI数量,提升特征建模精细度。选取武汉市作为实验区域,在街道尺度与WorldPop、GPW及中国公里网格人口数据集进行对比验证方法的有效性。结果表明,该方法的平均绝对值误差仅为对比数据集的1/6~1/3。此外,还探讨了特征构成、格网大小及核密度带宽对精度的影响。

Objectives:Existing population spatialization methods mainly use administrative-unit-level data to train regression model,and transfer it to grid cell-level to achieve population allocation.However,the significant scale difference between the analytical units in training and estimation leads to the issues of crossscale model transfer.Meanwhile,only the attributes of current cell are considered in cell-level feature modeling,which causes the innate spatial association between cells to be eliminated and cells to be isolated.Methods:This paper proposes a novel population spatialization based on random forest by considering pixellevel attribute grading and spatial association(PAG-SA).In the cell-level feature modeling,we firstly con⁃struct the night light grading features embedded with building category constraints based on natural breaks,and count the grid proportion of each grading level at the administrative-unit-level as the training input to reduce the cross scale error;secondly,the influence and distance attenuation of neighborhood point of in⁃terests(POIs)upon the current cell is modelled by using kernel density estimation;thirdly,based on over⁃lay analysis,the numbers of POIs in the contours of different building types are counted to improve the pre⁃cision of feature modeling.Results:To verify the effectiveness of the proposed method,we selected Wu⁃han city as the experimental area and compared its spatialization accuracy with the datasets of WorldPop,GPW and PopulationGrid_China at street scale.The results show that the mean absolute error of PAG⁃SA is only 1/6-1/3 of the comparison datasets.In addition,the influence of feature composition,grid size and kernel density bandwidth on the accuracy is also discussed.Conclusions:By fusing multi⁃source data and considering pixel⁃level attribute grading and spatial association,the proposed method PAG⁃SA is effective for achieving population spatialization in urban areas with finer grid sizes and higher accuracy.It can also provide references for spatialization applications of other geographic attributes that also face with scale mis⁃match issue in spatial regression modeling.