Visualization 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...
Published in: | Scandinavian Journal of Statistics |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | https://hdl.handle.net/1983/236ed031-4337-4eef-9bcb-a2acd5908028 https://research-information.bris.ac.uk/en/publications/236ed031-4337-4eef-9bcb-a2acd5908028 https://doi.org/10.1111/sjos.12234 https://research-information.bris.ac.uk/ws/files/67057769/sanity2a.pdf |
id |
ftubristolcris:oai:research-information.bris.ac.uk:publications/236ed031-4337-4eef-9bcb-a2acd5908028 |
---|---|
record_format |
openpolar |
spelling |
ftubristolcris:oai:research-information.bris.ac.uk:publications/236ed031-4337-4eef-9bcb-a2acd5908028 2024-01-28T10:01:39+01:00 Visualization for Large-scale Gaussian Updates Rougier, Jonathan Zammit Mangion, Andrew 2016-11-08 application/pdf https://hdl.handle.net/1983/236ed031-4337-4eef-9bcb-a2acd5908028 https://research-information.bris.ac.uk/en/publications/236ed031-4337-4eef-9bcb-a2acd5908028 https://doi.org/10.1111/sjos.12234 https://research-information.bris.ac.uk/ws/files/67057769/sanity2a.pdf eng eng info:eu-repo/semantics/openAccess Rougier , J & Zammit Mangion , A 2016 , ' Visualization for Large-scale Gaussian Updates ' , Scandinavian Journal of Statistics , vol. 43 . https://doi.org/10.1111/sjos.12234 medal plot spatial statistics variance bound variance update article 2016 ftubristolcris https://doi.org/10.1111/sjos.12234 2024-01-04T23:48:30Z 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 Bristol: Bristol Research Antarctic The Antarctic Scandinavian Journal of Statistics 43 4 1153 1161 |
institution |
Open Polar |
collection |
University of Bristol: Bristol Research |
op_collection_id |
ftubristolcris |
language |
English |
topic |
medal plot spatial statistics variance bound variance update |
spellingShingle |
medal plot spatial statistics variance bound variance update Rougier, Jonathan Zammit Mangion, Andrew Visualization for Large-scale Gaussian Updates |
topic_facet |
medal plot spatial statistics variance bound variance update |
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, Jonathan Zammit Mangion, Andrew |
author_facet |
Rougier, Jonathan Zammit Mangion, Andrew |
author_sort |
Rougier, Jonathan |
title |
Visualization for Large-scale Gaussian Updates |
title_short |
Visualization for Large-scale Gaussian Updates |
title_full |
Visualization for Large-scale Gaussian Updates |
title_fullStr |
Visualization for Large-scale Gaussian Updates |
title_full_unstemmed |
Visualization for Large-scale Gaussian Updates |
title_sort |
visualization for large-scale gaussian updates |
publishDate |
2016 |
url |
https://hdl.handle.net/1983/236ed031-4337-4eef-9bcb-a2acd5908028 https://research-information.bris.ac.uk/en/publications/236ed031-4337-4eef-9bcb-a2acd5908028 https://doi.org/10.1111/sjos.12234 https://research-information.bris.ac.uk/ws/files/67057769/sanity2a.pdf |
geographic |
Antarctic The Antarctic |
geographic_facet |
Antarctic The Antarctic |
genre |
Antarc* Antarctic Ice Sheet |
genre_facet |
Antarc* Antarctic Ice Sheet |
op_source |
Rougier , J & Zammit Mangion , A 2016 , ' Visualization for Large-scale Gaussian Updates ' , Scandinavian Journal of Statistics , vol. 43 . https://doi.org/10.1111/sjos.12234 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1111/sjos.12234 |
container_title |
Scandinavian Journal of Statistics |
container_volume |
43 |
container_issue |
4 |
container_start_page |
1153 |
op_container_end_page |
1161 |
_version_ |
1789326854675496960 |