Spatiotemporal clustering using Gaussian processes embedded in a mixture model

Show simple item record

dc.contributor.author Vanhatalo, Jarno
dc.contributor.author Foster, Scott D.
dc.contributor.author Hosack, Geoffrey R.
dc.date.accessioned 2021-10-20T06:13:01Z
dc.date.available 2021-10-20T06:13:01Z
dc.date.issued 2021-11
dc.identifier.citation Vanhatalo , J , Foster , S D & Hosack , G R 2021 , ' Spatiotemporal clustering using Gaussian processes embedded in a mixture model ' , Environmetrics , vol. 32 , no. 7 . https://doi.org/10.1002/env.2681
dc.identifier.other PURE: 163791464
dc.identifier.other PURE UUID: eae6f535-1620-4820-a878-70d1ea5e5f5d
dc.identifier.other WOS: 000647938500001
dc.identifier.uri http://hdl.handle.net/10138/335461
dc.description.abstract The categorization of multidimensional data into clusters is a common task in statistics. Many applications of clustering, including the majority of tasks in ecology, use data that is inherently spatial and is often also temporal. However, spatiotemporal dependence is typically ignored when clustering multivariate data. We present a finite mixture model for spatial and spatiotemporal clustering that incorporates spatial and spatiotemporal autocorrelation by including appropriate Gaussian processes (GP) into a model for the mixing proportions. We also allow for flexible and semiparametric dependence on environmental covariates, once again using GPs. We propose to use Bayesian inference through three tiers of approximate methods: a Laplace approximation that allows efficient analysis of large datasets, and both partial and full Markov chain Monte Carlo (MCMC) approaches that improve accuracy at the cost of increased computational time. Comparison of the methods shows that the Laplace approximation is a useful alternative to the MCMC methods. A decadal analysis of 253 species of teleost fish from 854 samples collected along the biodiverse northwestern continental shelf of Australia between 1986 and 1997 shows the added clarity provided by accounting for spatial autocorrelation. For these data, the temporal dependence is comparatively small, which is an important finding given the changing human pressures over this time. en
dc.format.extent 19
dc.language.iso eng
dc.relation.ispartof Environmetrics
dc.rights cc_by
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject clustering
dc.subject community ecology
dc.subject Gaussian process
dc.subject Laplace approximation
dc.subject mixture
dc.subject regions of common profiles
dc.subject spatial
dc.subject spatiotemporal
dc.subject DEMERSAL FISH
dc.subject SPATIAL DATA
dc.subject CLASSIFICATION
dc.subject INFERENCE
dc.subject SELECTION
dc.subject 111 Mathematics
dc.title Spatiotemporal clustering using Gaussian processes embedded in a mixture model en
dc.type Article
dc.contributor.organization Department of Mathematics and Statistics
dc.contributor.organization Organismal and Evolutionary Biology Research Programme
dc.contributor.organization Environmental and Ecological Statistics Group
dc.contributor.organization Biostatistics Helsinki
dc.contributor.organization Research Centre for Ecological Change
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1002/env.2681
dc.relation.issn 1180-4009
dc.rights.accesslevel openAccess
dc.type.version publishedVersion
dc.relation.funder SUOMEN AKATEMIA
dc.relation.grantnumber

Files in this item

Total number of downloads: Loading...

Files Size Format View
env.2681.pdf 3.497Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record