Detecting spatially non-stationary and scale-dependent relationships between urban landscape fragmentation and related factors using Geographically Weighted Regression

Gao, Jun; Li, Shuangcheng

doi:10.1016/j.apgeog.2010.06.003

Cited by 218 publications

(110 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When SI<1, the explanatory variable y and dependent variable x reach spatial stationarity (Gao and Li 2011). To identify the scale dependence of spatial nonstationarity in local parameter coefficients, we iterated the GWR model with increasing fixed kernel bandwidth from 25 to 1,500 km as the search radius.…”

Section: Measuring Nonstationaritymentioning

confidence: 99%

“…Recently, as an extension of traditional standard global regression techniques, geographically weighted regression (GWR) was developed to explore spatially varying relationships (Brunsdon et al 1998;Fotheringham et al 2002). A few studies have confirmed the analytical efficacy of GWR for investigating spatially varying relationships in some research fields, such as climatology (Brunsdon et al 2001), ecological inference problem (Calvo and Escolar 2003), forests (Shi et al 2006b), urban poverty (Longley and Tobón 2004), environmental justice (Mennis and Jordan 2005), urban land surface temperature (Li et al 2010), and urban landscape fragmentation (Gao and Li 2011). In recent years, a limited number of studies extended its scope into relationships between vegetation and climate (Gao et al 2012a, b;Gaughan et al 2012;Propastin et al 2008).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Exploring spatially variable relationships between NDVI and climatic factors in a transition zone using geographically weighted regression

Zhao

Gao

Wang

et al. 2014

Theor Appl Climatol

Self Cite

View full text Add to dashboard Cite

At landscape scale, the normalized difference vegetation index (NDVI) can be used to indicate the vegetation's dynamic characteristics and has been widely employed to develop correlated and dependent relationships with the climatic and environmental factors. However, studies show that NDVI-environment relationships always emerge with complex features such as nonlinearity, scale dependency, and nonstationarity, especially in highly heterogeneous areas. In this study, we used geographically weighted regression (GWR), a local modeling technique to estimate regression models with spatially varying relationships, to investigate the spatially nonstationary relationships between NDVI and climatic factors at multiple scales in North China. The results indicate that all GWR models with appropriate bandwidth represented significant improvements of model performance over the ordinary least squares (OLS) models. The spatial relationships between NDVI and climatic factors varied significantly over space and were more significant and sensitive in the ecogeographical transition zone. Clear spatial patterns of slope parameters and local coefficient of determination (R 2 ) were found from the results of the GWR models. Moreover, the spatial patterns of the local R 2 of NDVI-precipitation are much clearer than the R 2 of NDVI-temperature in the semiarid and subhumid areas, which mean that precipitation has more significant influence on vegetation in these areas. In conclusion, the study revealed detailed site information on the variable relationships in different parts of the study area, especially in the ecogeographical transition zone, and the GWR model can improve model ability to address spatial, nonstationary, and scale-dependent problems in landscape ecology.

show abstract

Section: Measuring Nonstationaritymentioning

confidence: 99%

mentioning

confidence: 99%

Exploring spatially variable relationships between NDVI and climatic factors in a transition zone using geographically weighted regression

Zhao

Gao

Wang

et al. 2014

Theor Appl Climatol

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, residuals of both OLS and GWR results were analysed using global Moran's I to test for spatial autocorrelation. If the results of global Moran's I on the residuals show significant p-values, there is spatial autocorrelation present and the results of the analysis may be unreliable (Brunsdon, Fotheringham, & Charlton, 1998;Fotheringham et al, 2002;Gao & Li, 2010). …”

Section: Global and Local Clusteringmentioning

confidence: 99%

Stray cats in Auckland, New Zealand: Discovering geographic information for exploratory spatial analysis

Aguilar

Farnworth

2012

Applied Geography

View full text Add to dashboard Cite

Stray cats are a common feature of urban landscapes and are associated with issues of animal welfare and negative environmental impacts. Management, planning and decision-making require readily accessible information on stray cats. However, much of the existing data is not immediately useful for a geographic information system (GIS) in terms of format, content and explicit location information. Spreadsheets we obtained from a single large shelter in the Auckland region. They contained records of stray cat pickups and admissions for an entire year (n = 8573) of which 56.4% (n = 4834) contained data that could be processed to derive relevant spatial information. The resulting data consisted of identified roads and areas of Auckland where the stray cats were found. Published census databases and shapefiles were matched with the data to build a GIS of stray cats. Global and local regression analysis was employed to discover spatial distribution characteristics including the identification of areas with relatively high and low concentrations of stray cats and to explore relationships between socioeconomic condition and stray cat density. Significant clustering is more evident in South Auckland than elsewhere in the region. Specific geographical information is valuable, not only for understanding population dynamics of stray cats, but also to allow spatial and temporal targeting of resources to minimise their impact and promote responsible ownership.

show abstract

“…Unlike OLS and spatial regression, in GWR the relationships between the independent and dependent variables are not assumed to be the same at all locations (Gao & Li, 2011). One of the common problems with estimating global regression models, like OLS and spatial regression, for spatial data are that 14 variations over space that might exist in the data are suppressed (Cahill & Mulligan, 2007).…”

Section: Modelling Frameworkmentioning

confidence: 99%

The effect of altitude and slope on the spatial patterning of burglary

Breetzke

2012

Applied Geography

View full text Add to dashboard Cite

Physical geography is significant for crime, and its presence or absence, yet no studies have investigated the relationship between crime and certain broader features of physical geography such as altitude, and slope. In this study I attempt to fill this gap by using OLS and geographically weighted regression to gauge the effect of altitude and slope on burglary patterns in Tshwane, South Africa. In the analysis I found considerable evidence that residing at a greater altitude reduces your risk of burglary victimization, although residing on steeper slopes had no effect. In the discussion I argue that the underlying relief and terrain on which neighborhoods are built should form an essential "physical" component of the environmental backcloth that surrounds offenders and influences their spatial decision making processes.

show abstract

Detecting spatially non-stationary and scale-dependent relationships between urban landscape fragmentation and related factors using Geographically Weighted Regression

Cited by 218 publications

References 32 publications

Exploring spatially variable relationships between NDVI and climatic factors in a transition zone using geographically weighted regression

Exploring spatially variable relationships between NDVI and climatic factors in a transition zone using geographically weighted regression

Stray cats in Auckland, New Zealand: Discovering geographic information for exploratory spatial analysis

The effect of altitude and slope on the spatial patterning of burglary

Contact Info

Product

Resources

About