Effectiveness of Remotely Sensed Built Areas for Constraining and Modelling Gridded Population Estimates - Script Samples and Data

These data present the effectiveness of three different high-resolution built area datasets for producing gridded population estimates through the dasymetric disaggregation of census counts in Haiti, Malawi, Madagascar, Nepal, Rwanda, and Thailand. Modeling techniques include a binary dasymetric redistribution, random forest with dasymetric component, and a hybrid of the previous two.

本数据集展示了三种不同的高分辨率建筑区域数据集，通过对海地、马拉维、马达加斯加、尼泊尔、卢旺达及泰国的普查人口数进行密度分区插值（dasymetric disaggregation）以生成栅格化人口估算值的有效性。所采用的建模技术包括二元密度分区重分配法、带密度分区模块的随机森林模型，以及前述两种方法的混合模型。