Skip to main content
placeholder image

Bayesian approaches to spatial inference: Modelling and computational challenges and solutions

Journal Article


Download full-text (Open Access)

Abstract


  • We discuss a range of Bayesian modelling approaches for spatial data and investigate some of the associated computational challenges. This paper commences with a brief review of Bayesian mixture models and Markov random fields, with enabling computational algorithms including Markov chain Monte Carlo (MCMC) and integrated nested Laplace approximation (INLA). Following this, we focus on the Potts model as a canonical approach, and discuss the challenge of estimating the inverse temperature parameter that controls the degree of spatial smoothing. We compare three approaches to addressing the doubly intractable nature of the likelihood, namely pseudo-likelihood, path sampling and the exchange algorithm. These techniques are applied to satellite data used to analyse water quality in the Great Barrier Reef.

Publication Date


  • 2014

Citation


  • Moores, M. & Mengersen, K. (2014). Bayesian approaches to spatial inference: Modelling and computational challenges and solutions. AIP Conference Proceedings, 1636 (1), 112-117.

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=2687&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1685

Number Of Pages


  • 5

Start Page


  • 112

End Page


  • 117

Volume


  • 1636

Issue


  • 1

Place Of Publication


  • United States

Abstract


  • We discuss a range of Bayesian modelling approaches for spatial data and investigate some of the associated computational challenges. This paper commences with a brief review of Bayesian mixture models and Markov random fields, with enabling computational algorithms including Markov chain Monte Carlo (MCMC) and integrated nested Laplace approximation (INLA). Following this, we focus on the Potts model as a canonical approach, and discuss the challenge of estimating the inverse temperature parameter that controls the degree of spatial smoothing. We compare three approaches to addressing the doubly intractable nature of the likelihood, namely pseudo-likelihood, path sampling and the exchange algorithm. These techniques are applied to satellite data used to analyse water quality in the Great Barrier Reef.

Publication Date


  • 2014

Citation


  • Moores, M. & Mengersen, K. (2014). Bayesian approaches to spatial inference: Modelling and computational challenges and solutions. AIP Conference Proceedings, 1636 (1), 112-117.

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=2687&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1685

Number Of Pages


  • 5

Start Page


  • 112

End Page


  • 117

Volume


  • 1636

Issue


  • 1

Place Of Publication


  • United States