Improving the Accuracy of Urban Environmental Quality Assessment Using Geographically-Weighted Regression Techniques

Abstract

Urban Environmental Quality (UEQ) can be treated as a generic indicator that objectively represents the physical and socio-economic condition of the urban and built environment. The value of UEQ illustrates a sense of satisfaction to its population through assessing different environmental, urban and socio-economic parameters. This paper elucidates the use of the Geographic Information System (GIS), Principal Component Analysis (PCA) and Geographically-Weighted Regression (GWR) techniques to integrate various parameters and estimate the UEQ of two major cities in Ontario, Canada. Remote sensing, GIS and census data were first obtained to derive various environmental, urban and socio-economic parameters. The aforementioned techniques were used to integrate all of these environmental, urban and socio-economic parameters. Three key indicators, including family income, higher level of education and land value, were used as a reference to validate the outcomes derived from the integration techniques. The results were evaluated by assessing the relationship between the extracted UEQ results and the reference layers. Initial findings showed that the GWR with the spatial lag model represents an improved precision and accuracy by up to 20% with respect to those derived by using GIS overlay and PCA techniques for the City of Toronto and the City of Ottawa. The findings of the research can help the authorities and decision makers to understand the empirical relationships among environmental factors, urban morphology and real estate and decide for more environmental justice.

COVID-19: District level vulnerability assessment in India

“…The Z-score is a widely used statistical technique that can able to standardize a wide range of data to represent the significant changes across the data. 41 Z-score data normalization has been done using the following formula 42 …”

Real Estate Values and Urban Quality: A Multiple Linear Regression Model for Defining an Urban Quality Index

“…Spatial data gathered were aggregated in a Geographic Information System (GIS) using Open Source QGIS software with which it was possible to weigh geographical data with statistical analysis [17] through normalization operations, obtaining empirical models that allow the reading of urban phenomena that contribute to the definition of qualityquantitative indices. Indicators were subsequently used for the elaboration of a multiple linear regression model on SPSS Statistical Analysis Software.…”

Geographically Weighted Method Integrated with Logistic Regression for Analyzing Spatially Varying Accuracy Measures of Remote Sensing Image Classification

“…The focus of our attention on GWR is motivated by numerous studies which have demonstrated its potential in the investigation of spatially varying relationships, including climatology (Brunsdon et al 2001 ; Khosravi and Balyani 2019 ; Wehbe et al 2020 ), health (Lin and Wen 2011 ; Ehlkes et al 2014 ; Weber 2018 ; Hong et al 2018 ; Hasyim et al 2018 ), real estate management (Lu et al 2014 ; Liu et al 2016 ), urban studies (Faisal and Shaker 2017 ; Wang et al 2020 ) and land change analysis (Maimaitijiang et al 2015 ; Dadashpoor et al 2019 ). GWR can also be applied in combination with linear, logistic and poisson regression techniques for various applications and reported in many studies (Nakaya et al 2005 ; Ehlkes et al 2014 ; Mayfield et al 2018 ).…”