The utility of built environment geospatial data for high-resolution dasymetric global population modeling. (March 2021)

• Record Type: Journal Article
• Authors: Rubinyi, Steven; Blankespoor, Brian; Hall, Jim W.
• Is Part Of: Computers, environment and urban systems. Volume 86(2021)
• Publication Date: 2021-03
• Subjects: Population modeling -- Built environment -- Demography -- Remote sensing; City planning -- Data processing -- Periodicals; Regional planning -- Data processing -- Periodicals; 303.4834
• DOI: 10.1016/j.compenvurbsys.2021.101594
• Languages: English
• ISSNs: 0198-9715

Abstract

Abstract: Several global gridded population data sets are available at unprecedented high-resolution, including recent releases at 100-m, 30-m, and 10-m resolution. These data sets are the result of the application of advanced methods to disaggregate census population counts from administrative units and facilitated by the proliferation of increasingly high-resolution spatial information pertaining to the built environment (e.g. built-up and building footprint data). Accordingly, these gridded population data are increasingly dependent on a single ancillary data set to inform the distribution of populations across space. Our study tests several combinations of binary masking variables (land areas, all building footprints, residential building footprints) and density variables (building footprint areas, building volumes) derived from characteristics of the built environment at 20× and 8000× downscaling using a flexible equation for high-resolution global dasymetric population modeling. The assessment is applied in New York City, where large spatial heterogeneities exist across confined geographic areas. Results confirm that the performance of the model generally improves as: (i) the binary masking variable becomes increasingly limiting; and, (ii) the density variable becomes more pronounced. However, application requires careful consideration due to their propensity to amplify both positive results and errors. Highlights: Built environment data are effective for global dasymetric population modeling. Relative effectiveness of model variations corresponds to the degree of downscaling. A more limiting binary mask consistently improved accuracy. Density variables increase accuracy but accentuate errors where present. Residential building footprint volumes outperformed all other model specifications.