Visualisation for large-scale Gaussian updates

In geostatistics and also in other applications in science and engineering, it is now common to perform updates on Gaussian process models with many thousands or even millions of components. These large-scale inferences involve modelling, representational and computational challenges. We describe a...

Full description

Bibliographic Details
Main Authors: Rougier, Jonathon, Zammit-Mangion, Andrew
Format: Article in Journal/Newspaper
Language:unknown
Published: Research Online 2016
Subjects:
Online Access:https://ro.uow.edu.au/eispapers/6611
https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7641&context=eispapers
id ftunivwollongong:oai:ro.uow.edu.au:eispapers-7641
record_format openpolar
spelling ftunivwollongong:oai:ro.uow.edu.au:eispapers-7641 2023-05-15T13:58:42+02:00 Visualisation for large-scale Gaussian updates Rougier, Jonathon Zammit-Mangion, Andrew 2016-01-01T08:00:00Z application/pdf https://ro.uow.edu.au/eispapers/6611 https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7641&context=eispapers unknown Research Online https://ro.uow.edu.au/eispapers/6611 https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7641&context=eispapers Faculty of Engineering and Information Sciences - Papers: Part A visualisation updates gaussian large-scale Engineering Science and Technology Studies article 2016 ftunivwollongong 2020-02-25T11:37:20Z In geostatistics and also in other applications in science and engineering, it is now common to perform updates on Gaussian process models with many thousands or even millions of components. These large-scale inferences involve modelling, representational and computational challenges. We describe a visualization tool for large-scale Gaussian updates, the 'medal plot'. The medal plot shows the updated uncertainty at each observation location and also summarizes the sharing of information across observations, as a proxy for the sharing of information across the state vector (or latent process). As such, it reflects characteristics of both the observations and the statistical model.We illustrate with an application to assess mass trends in the Antarctic Ice Sheet, for which there are strong constraints from the observations and the physics. Article in Journal/Newspaper Antarc* Antarctic Ice Sheet University of Wollongong, Australia: Research Online Antarctic The Antarctic
institution Open Polar
collection University of Wollongong, Australia: Research Online
op_collection_id ftunivwollongong
language unknown
topic visualisation
updates
gaussian
large-scale
Engineering
Science and Technology Studies
spellingShingle visualisation
updates
gaussian
large-scale
Engineering
Science and Technology Studies
Rougier, Jonathon
Zammit-Mangion, Andrew
Visualisation for large-scale Gaussian updates
topic_facet visualisation
updates
gaussian
large-scale
Engineering
Science and Technology Studies
description In geostatistics and also in other applications in science and engineering, it is now common to perform updates on Gaussian process models with many thousands or even millions of components. These large-scale inferences involve modelling, representational and computational challenges. We describe a visualization tool for large-scale Gaussian updates, the 'medal plot'. The medal plot shows the updated uncertainty at each observation location and also summarizes the sharing of information across observations, as a proxy for the sharing of information across the state vector (or latent process). As such, it reflects characteristics of both the observations and the statistical model.We illustrate with an application to assess mass trends in the Antarctic Ice Sheet, for which there are strong constraints from the observations and the physics.
format Article in Journal/Newspaper
author Rougier, Jonathon
Zammit-Mangion, Andrew
author_facet Rougier, Jonathon
Zammit-Mangion, Andrew
author_sort Rougier, Jonathon
title Visualisation for large-scale Gaussian updates
title_short Visualisation for large-scale Gaussian updates
title_full Visualisation for large-scale Gaussian updates
title_fullStr Visualisation for large-scale Gaussian updates
title_full_unstemmed Visualisation for large-scale Gaussian updates
title_sort visualisation for large-scale gaussian updates
publisher Research Online
publishDate 2016
url https://ro.uow.edu.au/eispapers/6611
https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7641&context=eispapers
geographic Antarctic
The Antarctic
geographic_facet Antarctic
The Antarctic
genre Antarc*
Antarctic
Ice Sheet
genre_facet Antarc*
Antarctic
Ice Sheet
op_source Faculty of Engineering and Information Sciences - Papers: Part A
op_relation https://ro.uow.edu.au/eispapers/6611
https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7641&context=eispapers
_version_ 1766267053387284480