Spatial non-stationarity analysis to estimate dwelling units in Riyadh, Saudi Arabia

Abstract

Dwelling unit (population) data at finer zones are important for different applications. The census data are not available every year and published at coarse zones. While the remotely sensed data have addressed this limitation, analysis of spatial non-stationarity in the relationship between dwelling and detailed urban remote-sensing covariates for dwelling estimates is almost novel. Riyadh, Saudi Arabia, is chosen as a case study. The remote-sensing variables have been derived from QuickBird data using an object-based image analysis. To analyse the spatial non-stationarity, ordinary least squares (OLS) and geographically weighted regression (GWR) approaches are applied. The OLS models suggest that utilizing three-residential classes provides more accurate results than built area and residential built area. The GWR models are more accurate than the OLS model. This research proves that the GWR approach cannot completely handle the spatial non-stationarity problem without efficient explanatory variables. For example, the GWR model that uses three-residential classes is the best model to estimate dwelling compared with the GWR model that uses residential built area. This article confirms that the application of the OLS approach with efficient explanatory variables can successfully account the spatial non-stationarity and the results are relatively comparable with the GWR model.

A Bivariate Dasymetric Population Map of Saudi Arabia

“…Whatever the approach, most of the cartographers agree that the dasymetric method has by far better results than the choropleth, isopleth and/or graded circles map methods for example, even when used in urban spaces. We refer here to the research conducted on Jeddah City (Hamza et al, 2016) or on Riyadh (Alahmadi et al, 2012(Alahmadi et al, , 2013(Alahmadi et al, , 2015(Alahmadi et al, , 2016Alahmadi, 2018).…”

“…Mostly, European, or North American countries were concerned by research works on the dasymetric method, whether addressing methodological or/and technical aspects, or case studies. In Arab countries, a few attempts were conducted (Jaullt & Serradj, 2011;Alahmadi et al, 2012Alahmadi et al, , 2015Alahmadi et al, , 2016Alahmadi et al, , 2018Hamza et al, 2016;Dhieb et al, 2021). Jaullt and Serraj used Remote Sensing and 2004 Tunisian Census to replace the biased choropleth data of Kairouan region (Tunisia) by a more realistic dasymetric map focusing on really populated data (Jaullt & Serradj, 2011).…”

“…In a third research, three statistical regression models were combined with two dasymetric areal interpolation models leading to six-classes proving that multivariate dasymetric mapping approach is more accurate than bivariate dasymetric mapping (2016). In a recent study, Alahmady used a spatial non-stationarity analysis to estimate dwelling units in Riyadh (Alahmadi, 2018).…”