Estimating the spatial distribution of the population of Riyadh, Saudi Arabia using remotely sensed built land cover and height data

• Published in: Computers, environment and urban systems Vol. 41; pp. 167 - 176
• Main Authors: Alahmadi, Mohammed, Atkinson, Peter, Martin, David
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.09.2013; Elsevier
• Subjects: Accuracy; Applied sciences; Buildings. Public works; Computation methods. Tables. Charts; Density; Dwelling; Dwellings; Estimates; Estimating; Estimation; Exact sciences and technology; Land cover; Mathematical models; Measurements. Technique of testing; Population; Riyadh; Structural analysis. Stresses; Urban development; Saudi Arabia; Asia; Saudi Arabia, Riyadh; Population; Dwelling; Land cover; Estimation; Riyadh; Site analysis; Spatial analysis; Built environment; Forecast model; Modeling; Land use; Remote sensing; Habitable space; Residential zone; Image analysis; Spatial distribution; Town
• ISSN: 0198-9715; 1873-7587
• DOI: 10.1016/j.compenvurbsys.2013.06.002

•A more advanced classification algorithm such as SVM provides more accurate results than ISODATA.•Remotely sensed height data, can be combined in different ways to aid estimation of dwelling units.•It is difficult for a single model to explain the complexity of dwelling distributions.•Study area stratification based on the building heights is effective in improving estimation of dwelling units. This paper investigates the use of Landsat ETM+, remotely sensed height data, ward-level census population, and dwelling units to downscale population in Riyadh, Saudi Arabia. Regression analysis is used to model the relationship between density of dwelling units and built area proportion at the block level and the coefficients used to downscale density of dwelling units to the parcel level. The population distribution is estimated based on average population per dwelling unit. Seven models were fitted and compared. First, a conventional approach, using ISODATA-classified built land cover alone as a covariate, is used as a benchmark against which to evaluate six more sophisticated models. The conventional model results in low accuracy measured by overall relative error (ORE) (+116%). Approaches for potentially increasing accuracy are explored, incorporating above-surface height data into the downscaling process. These include masking out zero and near-zero height areas when estimating built area; using height to estimate the number of floors; replacing the ISODATA model with a support vector machine; estimating volume-adjusted habitable space; stratifying the study area into different building categories; and preservation of the dependent variable for the best model. These approaches result in large increases in accuracy in the density of dwelling unit estimates. However, while the height data accounts for the vertical dimension (primarily through the number of floors), it is not possible to account for variation in dwelling density which arises due to other factors such as living standards, affluence and other spatially varying factors, without further data.