Geographically Weighted Regression Approach Research Articles

Modelling Gender Development Index in Central Java In 2021 with Geographically Weighted Regression

Regression analysis is a statistical analysis used to determine and model the influence of the relationship between one response variable and one or more predictor variables using the Ordinary Least Squares (OLS) method. In some cases involving spatial data, it can lead to violations of heterogeneity and autocorrelation, indicating the presence of spatial effects. One regression analysis that can address spatial effects is Geographically Weighted Regression (GWR). The Gender Development Index is an index used to measure the achievement of basic human development capabilities in various areas within a region, taking gender into consideration. This study aims to model the GDI of Central Java Province in 2021 using the GWR approach. The data used in this study are secondary data from 35 Districts/Cities in Central Java Province in 2021. Based on the GWR modeling analysis above, it can be concluded that the GWR model is the best model for modeling the GDI in Central Java Province in 2021 with an R2 value by 51.82% and AIC value of 159.0621. In the formed GWR model, the significant variables are X1 or average length of schooling, X4 or school participation rate, and X5 or gender ratio.

Spatio-Temporal Spread of Covid-19 in Children Aged 0-11 Years at Central Java Province Indonesia Using Geographical Weight Regression

During the COVID-19 pandemic, children under the age of 12 are the most vulnerable age group to health concerns. The goal of this study was to conduct a spatiotemporal analysis of the distribution of COVID-19 cases in Central Java children using the GWR (Geographically Weighted Regression) approach. The data source is the Central Java Provincial Health Office, and the study objects are 35 cities and districts in Central Java province. The data obtained are the number of COVID-19 cases in children aged 0-11 years, the total number of Covid-19 cases, the number of PCR tests per day, the number of vaccinations and the number of health care facilities per city and district per month from March 2020 to November 2021. Hotspot analysis and the GWR approach were used to examine data in semesters 1–4 (S1–S4). From S1 to S4, the number of COVID-19 cases in children increased. Areas that became hotspots for more than two semesters were Semarang City, Semarang Regency, Banyumas, Cilacap, Kendal, and Demak. According to the GWR analysis in S1-S4, the total number of COVID-19 cases, PCR tests per day, vaccinations, and health care facilities all affect the number of COVID-19 patients in children by more than 75%. The total number of COVID-19 cases has a significant impact on the number of COVID-19 cases in children but the number of health care facilities has no effect. The results of the GWR prediction of COVID-19 cases in children show that the cities of Semarang and Banyumas became areas with a larger number of COVID-19 cases in two semesters. According to the hotspot and GWR analysis, the cities of Semarang and Banyumas are regions to be on the lookout for in the spread of COVID-19 cases in S1-S4.

A Route Map for Successful Applications of Geographically Weighted Regression

Geographically Weighted Regression (GWR) is increasingly used in spatial analyses of social and environmental data. It allows spatial heterogeneities in processes and relationships to be investigated through a series of local regression models rather than a single global one. Standard GWR assumes that relationships between the response and predictor variables operate at the same spatial scale, which is frequently not the case. To address this, several GWR variants have been proposed. This paper describes a route map to decide whether to use a GWR model or not, and if so which of three core variants to apply: a standard GWR, a mixed GWR or a multiscale GWR (MS‐GWR). The route map comprises 3 primary steps that should always be undertaken: (1) a basic linear regression, (2) a MS‐GWR, and (3) investigations of the results of these in order to decide whether to use a GWR approach, and if so for determining the appropriate GWR variant. The paper also highlights the importance of investigating a number of secondary issues at global and local scales including collinearity, the influence of outliers, and dependent error terms. Code and data for the case study used to illustrate the route map are provided.

How is freight distribution affected by travel time unreliability?

The impact of travel time unreliability on freight transport has been extensively investigated in the last 20 years with the main focus being placed on mode and route choice (and using mostly stated preference data). In contrast, freight distribution has been very rarely examined in the literature. In this paper, we describe a study on how travel time unreliability affects interregional freight distribution using (revealed preference) data from the last national transport survey carried out in Iran (2015). Through this study, conducted using spatial interaction models and linear and geographically-weighted regression approaches, we found that, globally, travel time reliability is approximately as important as average travel time in determining freight distribution flows, but this importance varies widely across regions. We also found that tardy trip reliability measures describe freight distribution patterns more accurately than statistical range measures (coefficient of variation of travel time).

Spatial-scale dependent risk factors of heat-related mortality: A multiscale geographically weighted regression analysis

Extreme heat is a leading cause of weather-related human mortality throughout much of the world, posing a significantly heavy burden on the development of healthy and sustainable cities. To effectively reduce heat health risk, a better understanding of where and what risk factors should be targeted for intervention is necessary. However, little research has examined how different risk factors for heat-related mortality operate at varying spatial scales. Here, we present a novel application of the multiscale geographically weighted regression (GWR) approach to explore the scale of effect of each underlying risk factor using Hong Kong as a case study. We find that a hybrid of global and local processes via multiscale GWR yields a better fit of heat-related mortality risk than models using GWR and ordinary least squares (OLS) approaches. Predictor variables are categorized by the scale of effect into global variables (i.e., age and education attainment, socioeconomic status), intermediate variables (i.e., work place, birth place and language), and local variables (i.e., thermal environment, low income). These findings enrich our understanding of the spatial scale-dependent risk factors for heat-related mortality and shed light on the importance of hierarchical policy-making and site-specific planning processes in effective heat hazard mitigation and climate adaptation strategies.

Examining Opioid Overdose Deaths across Communities Defined by Racial Composition: a Multiscale Geographically Weighted Regression Approach

To provide data that can guide community-targeted practices, policies, and interventions in urban metropolitan areas, we used geospatial analysis to examine the community-level opioid overdose death determinants and their spatial variation across a study area. We obtained spatial datasets containing multiple, high-quality measures of socioeconomic conditions, public health status, and demographics for analysis and visualization in geographic information systems. We employed a multiscale modeling approach (multiscale geographically weighted regression; MGWR) to provide a comprehensive and robust analysis of opioid overdose death determinants, explain how geospatial patterns vary across scales across Milwaukee County in 2019, and examine the differential influence of factors locally, regionally, and globally. We subsequently examined how associations varied with the racial/ethnic composition of communities by dividing Milwaukee County into White-majority, Black-majority, and Hispanic-majority regions according to census data and conducting separate, independent modeling processes. Overall, the multiscale model explained 83% of opioid overdose death variability across neighborhoods in Milwaukee County using 12 selected variables. Statistical analysis and geovisualization of patterns, trends, and clusters using MGWR unveiled dramatic racialized health disparities in Milwaukee, showing how factors that influenced opioid overdose deaths varied across diverse communities in Milwaukee. The observed geographic variation in relationships included the impact of naloxone availability and incarceration rates on overdose deaths with pronounced differences between White communities and communities of color. Understanding, community-level factors that contribute to overdose risk should guide targeted community-level solutions. Overall, our findings demonstrate the value of precision epidemiology using MGWR analysis for defining and guiding responses to public health challenges.Supplementary InformationThe online version contains supplementary material available at 10.1007/s11524-021-00554-x.

Spatial Variability of Typhoid Disease Incidences in Uganda Using Geographically Weighted Regression Approach

The spatial variability of typhoid disease incidences has not been accounted for, most especially in developing countries, which makes its surveillance inefficient and expensive. This research aimed at (i) exploring possible risk factors of typhoid disease and (ii) accounting for spatial variability of typhoid disease incidences using GWR approach. The research first explored possible risk factors of typhoid disease using global regression-Ordinary Least Squares (OLS). Geographically Weighted Regression (GWR) model was used to account for spatial variability of typhoid disease incidences. Moran’s Index was used to confirm spatial patterns in the data. The research revealed that; poor handwashing practice, rainfall and poor drainage (floods effect) were responsible for spatial variability of typhoid disease locally (P<0.05). GWR model revealed that poor handwashing practice was mainly responsible for typhoid disease occurrences in Northern, Northwestern and Mid-central parts of the country while excessive rainfall was mainly responsible for occurrence of the disease in the Eastern and Western regions. Poor drainage was mainly influencing disease occurrences in Eastern and Southwestern parts of the country. In the analysis, GWR model performed better than global OLS model (R-squared=0.37, R-squared=0.25 respectively). A combination of poor handwashing practice, excessive rainfall and poor drainage accounts for spatial variability of typhoid disease incidences in Uganda. This knowledge is very essential for surveillance teams to (i) enforce preventive measures, (ii) prepare for outbreaks and (iii) make targeted interventions to eventually reduce operational costs.

Evaluating the NDVI–Rainfall Relationship in Bisha Watershed, Saudi Arabia Using Non-Stationary Modeling Technique

The Normalized Difference Vegetation Index (NDVI) and rainfall data were used to model the spatial relationship between vegetation and rainfall. Their correlation in previous studies was typically based on a global regression model, which assumed that the correlation was constant across space. The NDVI–rainfall association, on the other hand, is spatially non-stationary, non-linear, scale-dependent, and influenced by local factors (e.g., soil background). In this study, two statistical methods are used in the modeling, i.e., traditional ordinary least squares (OLS) regression and geographically weighted regression (GWR), to evaluate the NDVI–rainfall relationship. The GWR was implemented annually in the growing seasons of 2000 and 2016, using climate data (Normalized Vegetation Difference Index and rainfall). The NDVI–rainfall relationship in the studied Bisha watershed (an eco-sensitive zone with a complex landscape) was found to have a stable operating scale of around 12 km. The findings support the hypothesis that the OLS model’s average impression could not accurately represent local conditions. By addressing spatial non-stationarity, the GWR approach greatly improves the model’s accuracy and predictive ability. In analyzing the relationship between NDVI patterns and rainfall, our research has shown that GWR outperforms a global OLS model. This superiority stems primarily from the consideration of the relationship’s spatial variance across the study area. Global regression techniques such as OLS can overlook local details, implying that a large portion of the variance in NDVI is unexplained. It appears that rainfall is the most significant factor in deciding the distribution of vegetation in these regions. Furthermore, rainfall had weak relationships with areas predominantly located around wetlands, suggesting the need for additional factors to describe NDVI variations. The GWR method performed better in terms of accuracy, predictive power, and reduced residual autocorrelation. Thus, GWR is recommended as an explanatory and exploratory technique when relations between variables are subject to spatial variability. Since the GWR is a local form of spatial analysis that aligned to local conditions, it has the potential for more accurate prediction; however, a larger amount of data is needed to allow a reliable local fitting.

Non-Stationary Modeling of Microlevel Road-Curve Crash Frequency with Geographically Weighted Regression

Vehicle crashes on roads are caused by many factors. However, the influence of these factors is not necessarily homogenous across locations, which is a challenge for non-stationary modeling approaches. To address this problem, this paper adopts two types of methods allowing parameters to fluctuate among observations, that is, the random parameter approach and the geographically weighted regression (GWR) approach. With road curvature, curve length, pavement friction, and traffic volume as independent variables, vehicle crash frequencies are modeled by two non-spatial methods, including the negative binomial (NB) model and random parameter negative binomial (RPNB), as well as three spatial methods (GWR approach). These models are calibrated in microlevel using a dataset of 9415 horizontal curve segments with a total length of 1545 kilometers for a period of three years (2016–2018) over the State of Indiana. The results revealed that the GWR approach can capture spatial heterogeneity and therefore significantly outperforms the conventional non-spatial approach. Based on the Akaike Information Criterion (AICc), geographically weighted negative binomial regression (GWNBR) was proved to be a superior approach for statewide microlevel crash analysis.

EMS Response Time for Patients Critically-Injured from Automobile Accidents Using Regression Analysis

Background: The ability to quickly and effectively receive medical treatment in the event of an automobile collision is one of the most important aspects in emergency medical services (EMS). Emergency medical service providers are the first to respond and manage cases related to trauma, emergency surgery, and critically injured patients. Response time for emergency medical services vehicles is especially important for areas, where travel distances are often much larger, compared to more urban areas. The importance of the present data and analysis procedures are their applicability to multiple environments, including urban settings. Methods: The present study is focused on optimization of analysis tools, and understanding the influences of different traffic-related variables, related to hospital EMS transport times for Pickens County, a county in west Alabama. Optimization of associated analysis tools is important for optimal trauma patient survivability, and as such, is directly relevant to the management of care for severely injured surgical patients. Of particular interest are the effects of variables, such as travel time, time of the day, day of the week, weather, lighting conditions, and crash severity, on the EMS response time (ERT), which are analyzed using two types of advanced regression analysis: geographically weighted regression (GWR) and global regression analysis (GRA). Results: For GWR analysis, the accuracy of the approach is improved by employing an adaptive bi-square kernel weighting function. The GWR approach is also unique because geographic location variations are quantified for local independent variables, as their effects are included. Magnitudes of variable coefficients, and variable t-statistic values provide information on the relative influences and impacts of different variables, and different variable combinations, as they are considered in pairs, triplets, and different combinations. Conclusion: The resulting effects and alterations to optimal EMS response time are provided for a wide range of travel conditions and travel time periods.

Short‐Term Rental Platform in the Urban Tourism Context: A Geographically Weighted Regression (GWR) and a Multiscale GWR (MGWR) Approaches

This article contributes to advancing the knowledge on the phenomenon of the most popular short‐term rental platforms, Airbnb. By implementing a geographically weighted regression (GWR) and its multiscale form, MGWR, we examine the relationship between Airbnb locations and the core elements of urban tourism including hotels, food and beverages (F&amp;B) venues, as well as access to public transport. This article’s contributions are twofold: methodological and empirical. First, the results show that incorporating localities improve overall model performance. It allows us to account for the nuance of each area of interest as the MGWR performs slightly better than the GWR in the case of spatially sparse data. Second, both models show that Airbnbs collocate with hotels supported by various amenities, but Airbnbs also go beyond traditional hotel zones. This analysis highlights and extends the latter where Airbnb concentrations are those for which there are strong associations with F&amp;B establishments and access to public transports. This suggests that Airbnbs might benefit local businesses outside the reach of major tourist zones. However, there is further work to be done to understand whether the economic benefit to the local economy is worth the associated social costs raised by previous studies.

GEOGRAPHICALLY WEIGHTED REGRESSION APPROACH FOR SHALLOW WATER DEPTH ESTIMATION USING MULTISPECTRAL SATELLITE IMAGERIES

Abstract. Shallow water depth is essential for coastal planning, monitoring, and research. Bathymetry data is mostly produced from hydrographic survey using echosounder. The generic result from those measurements is discrete values while the desired output is a continuous depth model. To fill the gaps in the sounding data, we use Satellite Derived Bathymetry (SDB) approach with Geographically Weighted Regression (GWR). This study aims to investigate the feasibility of GWR to model bathymetry of shallow water in the eastern part of Indonesia. We explore the correlation between the number of training data and the predicted result. Two different satellites images are used, namely: Sentinel-2A and Landsat 8 OLI/TIRS with 10 and 30 m resolutions respectively. For the experiment, in-situ data are set into training and validation in three different ratios. The model is developed using adaptive GWR approach in which the parameter of regression would adapt the local data set within different kernel sizes. Finally, we compute RMSE (Root Mean Square Error), R2, and TVU (Total Vertical Uncertainty) to assess the quality of our model. In general, Sentinel-2A produces more detailed information due to higher resolution than Landsat 8 OLI/TIRS. Sentinel-2A also obtains more accurate results based on RMSE values. The percentage number of the estimated depth that fulfils TVU requirements is up to 83%. These assessment quality results give us an insight that the SDB approach using GWR is promising. Thus, the GWR method may be able to provide an estimate of bathymetry for many coastal areas in Indonesia.

GRACE: Gravity Recovery and Climate Experiment long-term trend investigation over the Nile River Basin: Spatial variability drivers

GRACE (Gravity Recovery and Climate Experiment) long-term terrestrial water storage anomaly (TWSA) is attributed to the complex interaction of climatic, physical and anthropogenic drivers. This paper, therefore, explores how different hydroclimatic and anthropogenic processes interact and combine over “space” to produce the mass variations that GRACE-TWSA detects. Using the Nile River Basin (NRB) as a case study, it explicitly analyzes nine hydroclimatic and anthropogenic processes, as well as their relationship to the TWSA in different climatic zones. The analytic method employed the long-term trends derived for both the dependent (TWSA) and independent (explanatory) variables via applying two geographically multiple regression (GMR) approaches: (i) an ordinary least square regression (OLS) model in which the contributions of all variables to TWSA variability are deemed equal at all locations; and (ii) a geographically weighted regression (GWR) which assigns a weight to each variable at different locations based on clustering occurrences. The models’ efficacy was investigated using standard goodness of fit diagnostics. The OLS explains that the basin at large TWSA spatial variability significantly attributed to five variables, i.e., precipitation, runoff, surface water storage, soil moisture storage, and population density, (p < 0.0001). The OLS model, however, produced an R2 value of 0.14 with skewed standardized residuals. In contrast, the GWR model retained varying explanatory variables by different climate zone. For instance, the results showed that all nine variables contribute significantly, with varying ranking, to the trend in TWSA in the tropical zone. The evapotranspiration (ET) and population density are the only significant variables in the semiarid zone; population density contributes significantly to TWSA variability in all zones. The GWR model yielded R2 values with a median of 0.71 and normally distributed standard residuals. To evaluate the robustness of the GWR approach, the basin-wide TWSA pattern was simulated using the GWR model outputs. Herein, the GWR highlights the importance of the spatial locations to attribute the spatial variability in GRACE TSWA long-term trends. This spatial information, therefore, is critical for developing robust statistical models for reconstructing time series of proxy GRACE anomalies that predate the launch of the GRACE and for gap-filling between GRACE and GRACE Follow-On (GRACE-FO) mission.

RNN-GWR: A geographically weighted regression approach for frequently updated data

Geographically weighted regression (GWR) is a local spatial regression technique to model varying relationships in many application domains, such as ecology, environmental management, public health, meteorology, and tourism. In the literature, most of the studies dealing with GWR do not take into account if the dataset is frequently updated and so these techniques are not efficient to handle such datasets. In this study, to handle frequently updated data on given locations, a computationally efficient GWR approach, RNN-GWR, which utilizes reverse nearest neighbor (RNN) strategy, is proposed. The performance of the proposed RNN-GWR approach is compared with the performances of a Naïve-GWR and FastGWR approaches. Experimental evaluations show that the proposed approach is computationally efficient than the other approaches on handling frequently updated data.

Prediction mapping of human leptospirosis using ANN, GWR, SVM and GLM approaches

BackgroundRecent reports of the National Ministry of Health and Treatment of Iran (NMHT) show that Gilan has a higher annual incidence rate of leptospirosis than other provinces across the country. Despite several efforts of the government and NMHT to eradicate leptospirosis, it remains a public health problem in this province. Modelling and Prediction of this disease may play an important role in reduction of the prevalence.MethodsThis study aims to model and predict the spatial distribution of leptospirosis utilizing Geographically Weighted Regression (GWR), Generalized Linear Model (GLM), Support Vector Machine (SVM) and Artificial Neural Network (ANN) as capable approaches. Five environmental parameters of precipitation, temperature, humidity, elevation and vegetation are used for modelling and predicting of the disease. Data of 2009 and 2010 are used for training, and 2011 for testing and evaluating the models.ResultsResults indicate that utilized approaches in this study can model and predict leptospirosis with high significance level. To evaluate the efficiency of the approaches, MSE (GWR = 0.050, SVM = 0.137, GLM = 0.118 and ANN = 0.137), MAE (0.012, 0.063, 0.052 and 0.063), MRE (0.011, 0.018, 0.017 and 0.018) and R2 (0.85, 0.80, 0.78 and 0.75) are used.ConclusionResults indicate the practical usefulness of approaches for spatial modelling and predicting leptospirosis. The efficiency of models is as follow: GWR > SVM > GLM > ANN. In addition, temperature and humidity are investigated as the most influential parameters. Moreover, the suitable habitat of leptospirosis is mostly within the central rural districts of the province.

Geospatial modeling approaches for mapping topsoil organic carbon stock in northern part of Mongolia

Soil organic carbon (SOC) is one of the most important indicators of soil quality and agricultural productivity. This paper presents the application of Regression Kriging (RK), geographically weighted regression (GWR) and Geographically Weighted Regression Kriging (GWRK) for prediction of topsoil organic carbon stock in Tarialan. A total of 25 topsoil (0-30 cm) samples were collected from Tarialan soum of Khuvsgul aimag in Mongolia. In this study, seven independent variables were used including normalised difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), normalised difference moisture index (NDMI), land surface temperature (LST) and terrain factors (DEM, Slope, Aspect). We used root-mean-square error (RMSE), mean error (ME) and determination coefficient (R2) to evaluate the performance of these methods. Validation results showed that performance of the GWRK, GWR, and RK approaches were good with not only low values of root-mean-square error (1.38 kg/m2, 1.48 kg/m2, 0.69 kg/m2), mean error (0.28 kg/m2, -0.22 kg/m2, 0.17 kg/m2) but also high values of R2 (0.76, 0.72, 0.94). The estimated SOC stock values ranged from 0.28-16.26 kg/m2, 0.72–15.24 kg/m2, 0.16–15.83 kg/m2 using GWRK, GWR, RK approaches in the study area. The highest average SOC stock value was in the wetland (6.47 kg/m2, 6.08 kg/m2, 6.44 kg/m2) and the lowest was in cropland (1.63 kg/m2, 1.48 kg/m2, 1.80 kg/m2) using these approaches. According to the validation, GWRK, GWR, and RK approaches produced satisfactory results for estimating and mapping SOC stock. However, Regression Kriging was the best model, followed by GWRK and GWR to predict topsoil organic carbon stock in Tarialan.

Spatial Heterogeneity in the Determinants of Urban Form: An Analysis of Chinese Cities with a GWR Approach

It is of great significance to investigate the determinants of urban form for shaping sustainable urban form. Previous studies generally assumed the determinants of urban form did not vary across spatial units, without taking spatial heterogeneity into account. In order to advance the theoretical understanding of the determinants of urban form, this study attempted to examine the spatial heterogeneity in the determinants of urban form for 289 Chinese prefecture-level cities using a geographically weighted regression (GWR) method. The results revealed the spatially varying relationship between urban form and its underlying factors. Population growth was found to promote urban expansion in most Chinese cities, and decrease urban compactness in part of the Chinese cities. Cities with larger administrative areas were more likely to have dispersed urban form. Industrialization was demonstrated to have no impact on urban expansion in cities located in the eastern coastal region of China, which constitutes the country’s most developed regions. Local financial revenue was found to accelerate urban expansion and increase urban shape irregularity in many Chines cities. It was found that fixed investment exerted a bidirectional impact on urban expansion. In addition, urban road networks and public transit were also identified as the determinants of urban form for some cities, which supported the complex urban systems (CUS) theory. The policy implications emerging from this study lies in shaping sustainable urban form for China’s decision makers and urban planners.

Hyper-local geographically weighted regression: extending GWR through local model selection and local bandwidth optimization

Geographically weighted regression (GWR) is an inherently exploratory technique for examining process non-stationarity in data relationships. This paper develops and applies a hyper-local GWR which extends such investigations further. The hyper-local GWR simultaneously optimizes both local model selection (which covariates to include in each local regression) and local kernel bandwidth specification (how much data should be included locally). These are evaluated using a measure of model fit. The hyper-local GWR approach evaluates different kernel bandwidths at each location and selects the most parsimonious local regression model. By allowing models and bandwidths to vary locally, this approach extends and refines the one-size-fits-all "whole map model" and "constant bandwidth calibration" under standard GWR. The results provide an alternative, complementary and more nuanced interpretation of localized regression. The method is illustrated using a case study modeling soil total nitrogen (STN) and soil total phosphorus (STP) from data collected at 689 locations in a watershed in Northern China. The analysis compares linear regression, standard GWR, and hyper-local GWR models of STN and STP and highlights the different locations at which covariates are identified as significant predictors of STN and STP by the different GWR approaches and the spatial variation in bandwidths. The hyper-local GWR results indicate that the STN processes are more non-stationary and localized than found via a standard application of GWR. By contrast, the results for STP are more confirmatory (i.e., similar) between the two GWR approaches providing extra assurance about the nature of the moderate non-stationary relationships observed. That is, a standard GWR may underestimate localized spatial heterogeneity where it is strongly present (as in the STN case study) and may overestimate it where spatial homogeneity is present (as in the STP case study). The overall benefits of hyper-local GWR are discussed, particularly in the context of the original investigative aims of GWR. A hyper-local approach provides a useful counter view of local regression modeling to that found with standard GWR. Where spatial non-stationarity exists, the hyper-local GWR provides a more spatially nuanced indication of the localization than a standard GWR analysis and can be used to suggest the direction of further analyses and investigations. Some areas of further work are suggested.

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

ABSTRACTDwelling 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.

Urban development patterns and exposure to hazardous and protective traffic environments

Estimates of the proportion of the U.S. population living close to high-traffic roads range from four to 19%. These proportions are higher for minority and low-income populations. Although the relationships among traffic exposure, race, and socioeconomic status have been consistent and reproducible, they are spatially heterogeneous and there has been limited investigation into the patterns heterogeneity. Using a spatially-explicit global regression and an exploratory geographically weighted regression (GWR), we examined variation in residential exposure to traffic at regional and neighborhood scales. Race/ethnicity, income, and college attainment are our variables of interest. Consistent with prior studies, we found that minority and lower socioeconomic status are systematically linked to higher exposure to traffic. Furthermore, the GWR approach has the potential to uncover patterns of disparities at a more localized level. However, a richer set of land use variables needs to be evaluated within this framework.