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

A - Papers appearing in refereed journals

Comber, A., Wang, Y., Lu, Y., Zhang, X. and Harris, P. 2018. Hyper-local geographically weighted regression: extending GWR through local model selection and local bandwidth optimization. Journal of Spatial Information Science. 17, pp. 63-84. https://doi.org/10.5311/JOSIS.2018.17.422

AuthorsComber, A., Wang, Y., Lu, Y., Zhang, X. and Harris, P.

Abstract: 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. By allowing models and bandwidths to vary locally, it extends the ’whole map model’ and ’constant bandwidth calibration’ under standard GWR. It provides an alternative and complementary 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 optimal bandwidths. The hyper-local GWR results indicate that the STN relationship 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 to the nature of the moderate non-stationary relationships observed. The overall benefits of hyper-local GWR are discussed, particularly in the context of the original investigative aims of standard GWR. Some areas of further work are suggested.

KeywordsLoess Plateau; GWR; Model selection; Spatial analysis
Year of Publication2018
JournalJournal of Spatial Information Science
Journal citation17, pp. 63-84
Digital Object Identifier (DOI)https://doi.org/10.5311/JOSIS.2018.17.422
Open accessPublished as green open access
FunderBiotechnology and Biological Sciences Research Council
National Natural Science Foundation of China
Natural Environment Research Council
Funder project or codeThe North Wyke Farm Platform [2012-2017]
Modelling and managing critical zone relationships between soil, water and ecosystem processes across the Loess Plateau
Publisher's version
Output statusPublished
Publication dates
Online17 Dec 2018
Publication process dates
Accepted05 Sep 2016
PublisherUniversity of Maine Press
Copyright licenseCC BY

Permalink - https://repository.rothamsted.ac.uk/item/8489q/hyper-local-geographically-weighted-regression-extending-gwr-through-local-model-selection-and-local-bandwidth-optimization

144 total views
246 total downloads
1 views this month
3 downloads this month
Download files as zip