PNNL

Abstract

Population data is normally collected at census administrative level, and areal interpolation of population is often required to transform population to the desired spatial resolution. Building footprint datasets, such as Microsoft building footprints, has proven to be useful in estimating population distribution and can therefore be used for areal interpolation of population. In addition to Microsoft building footprints, the recently released USA Structures dataset provides additional information such as building type and building height for some regions, which may provide valuable information for a better depiction of population distribution and thus improving population areal interpolation accuracy. In this study, we have conducted areal interpolation of population projections consistent with three different Shared Socioeconomic Pathways (SSP2, SSP3, and SSP5) from 1-km grid cells to block level in Washington state for every five years from 2020 to 2045 based on USA Structures. We assessed USA Structures-based population downscaling accuracy using U.S. decennial survey data in 2020 under three different downscaling scenarios, including population downscaling from census tracts to block groups, from census tracts to blocks, and from block groups to blocks. The resulting accuracies were compared with those based on Microsoft building footprints. The comparison showed that USA Structures achieved higher accuracies across different population density regions and areas with different urbanization extent