A dataset of permanent resident population density in Henan Province(2020)
High-precision population spatial data play an extremely important role in urban resource allocation and planning.To address the problem that current public population datasets fall short detailed regional research,this study integrates night light data,POI data,land cover data and topographic data to establish a comprehensive feature database for the spatial population density model.In this study,we used a Bayesian optimized LightGBM model(BO-LightGBM)to model township(subdistrict)population in Henan Province in 2020,and retrieved the spatial distribution of population density in Henan Province with a resolution of 200 meters.Using the data of the seventh population census for verification,the model achieved a coefficient of determination R2 of 0.934,an average absolute error of 0.134,and a mean square error of 0.034.Compared with the WorldPop dataset,the results of population spatialization in this study prove to be feasible and accurate,and can effectively reflect the population density of Henan Province in 2020.This dataset can be used for more precise population spatial analysis.
spatial population densityBayesian optimizationLightGBM modelHenan Provincemulti-source data
万方数据
维普
