Multiscale spatially varying coefficient modelling using a Geographical Gaussian Process GAM

A - Papers appearing in refereed journals

Comber, A, Harris, P. and Brunsdon, C 2023. Multiscale spatially varying coefficient modelling using a Geographical Gaussian Process GAM. International Journal Of Geographical Information Science. 38 (1), pp. 27-47. https://doi.org/10.1080/13658816.2023.2270285

AuthorsComber, A, Harris, P. and Brunsdon, C
Abstract

This paper proposes a novel spatially varying coefficient (SVC) regression through a Geographical Gaussian Process GAM (GGPGAM): a Generalized Additive Model (GAM) with Gaussian Process (GP) splines parameterised at observation locations. A GGP-GAM was applied to multiple simulated coefficient datasets exhibiting varying degrees of spatial heterogeneity and out-performed the SVC brand-leader, Multiscale Geographically Weighted Regression (MGWR), under a range of fit metrics. Both were then applied to a Brexit case study and compared, with MGWR marginally out-performing GGP-GAM. The theoretical frameworks and implementation of both approaches are discussed: GWR models calibrate multiple models whereas GAMs provide a full single model; GAMs can automatically penalise local collinearity; GWR-based approaches are computationally more demanding; MGWR is still only for Gaussian responses; MGWR bandwidths are intuitive indicators of spatial heterogeneity. GGP-GAM calibration and tuning are also discussed and areas of future work are identified, including the creation of a user-friendly package to support model creation and coefficient mapping, and to facilitate ease of comparison with alternate SVC models. A final observation that GGP-GAMs have the potential to overcome some of the long-standing reservations about GWRbased regression methods and to elevate the perception of SVCs amongst the broader community.

KeywordsSpatial regression; GWR
Year of Publication2023
JournalInternational Journal Of Geographical Information Science
Journal citation38 (1), pp. 27-47
Digital Object Identifier (DOI)https://doi.org/10.1080/13658816.2023.2270285
Open accessPublished as ‘gold’ (paid) open access
FunderNatural Environment Research Council
Biotechnology and Biological Sciences Research Council
Funder project or codeMIDST-CZ: Maximising Impact by Decision Support Tools for sustainable soil and water through UK-China Critical Zone science
Resilient Farming Futures
The North Wyke Farm Platform- National Capability [2023-28]
Publisher's version
Supplemental file
Output statusPublished
Publication dates
Online27 Oct 2023
Publication process dates
Accepted04 Oct 2023
PublisherTaylor & Francis
ISSN1365-8816

Permalink - https://repository.rothamsted.ac.uk/item/98y7z/multiscale-spatially-varying-coefficient-modelling-using-a-geographical-gaussian-process-gam

50 total views
15 total downloads
1 views this month
0 downloads this month
Download files as zip