Inference in cylindrical models having latent Markovian classes - with an application to ocean current data
Spatial direction vector data can be represented cylindrically by linear magnitudes and circular angles. We analyze such data by using a hierarchical Markov random field model with latent discrete classes and conditionally independent cylindrical data given the classes. The structure of a Potts mode...
Published in: | Spatial Statistics |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier Science
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/11250/2737939 https://doi.org/10.1016/j.spasta.2021.100497 |
id |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2737939 |
---|---|
record_format |
openpolar |
spelling |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2737939 2023-05-15T17:47:06+02:00 Inference in cylindrical models having latent Markovian classes - with an application to ocean current data Lie, Henrik Syversveen Eidsvik, Jo 2021 application/pdf https://hdl.handle.net/11250/2737939 https://doi.org/10.1016/j.spasta.2021.100497 eng eng Elsevier Science Norges forskningsråd: 305445 Spatial Statistics. 2021, 41, . urn:issn:2211-6753 https://hdl.handle.net/11250/2737939 https://doi.org/10.1016/j.spasta.2021.100497 cristin:1903533 Navngivelse 4.0 Internasjonal http://creativecommons.org/licenses/by/4.0/deed.no CC-BY 41 Spatial Statistics 100497 Peer reviewed Journal article 2021 ftntnutrondheimi https://doi.org/10.1016/j.spasta.2021.100497 2021-04-21T22:34:38Z Spatial direction vector data can be represented cylindrically by linear magnitudes and circular angles. We analyze such data by using a hierarchical Markov random field model with latent discrete classes and conditionally independent cylindrical data given the classes. The structure of a Potts model segments the spatial domain, and each class defines a cylindrical density that represents a specific structure. We consider two types of cylindrical distributions; the Weibull sine-skewed von Mises distribution, which is skewed in the circular part, and the generalized Pareto-type wrapped Cauchy distribution, which is heavy-tailed in the linear part. In this setting, we develop a statistically efficient block composite likelihood method for parameter estimation. The method is shown to provide much faster convergence than an expectation–maximization approach. However, the convergence is less stable for the block composite likelihood method, and we suggest a hybrid estimation approach for practical use. We apply the approach to study ocean surface currents in the Norwegian Sea. The models are able to describe the currents in terms of interpretable local regimes of two–three classes. Scoring rules are used to measure predictive performance of the two cylindrical densities. Results indicate that there is clearly skew angular components, and possibly also some heavy tails in magnitude. publishedVersion This is an open access article distributed under the terms of the Creative Commons CC-BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Article in Journal/Newspaper Norwegian Sea NTNU Open Archive (Norwegian University of Science and Technology) Norwegian Sea Spatial Statistics 41 100497 |
institution |
Open Polar |
collection |
NTNU Open Archive (Norwegian University of Science and Technology) |
op_collection_id |
ftntnutrondheimi |
language |
English |
description |
Spatial direction vector data can be represented cylindrically by linear magnitudes and circular angles. We analyze such data by using a hierarchical Markov random field model with latent discrete classes and conditionally independent cylindrical data given the classes. The structure of a Potts model segments the spatial domain, and each class defines a cylindrical density that represents a specific structure. We consider two types of cylindrical distributions; the Weibull sine-skewed von Mises distribution, which is skewed in the circular part, and the generalized Pareto-type wrapped Cauchy distribution, which is heavy-tailed in the linear part. In this setting, we develop a statistically efficient block composite likelihood method for parameter estimation. The method is shown to provide much faster convergence than an expectation–maximization approach. However, the convergence is less stable for the block composite likelihood method, and we suggest a hybrid estimation approach for practical use. We apply the approach to study ocean surface currents in the Norwegian Sea. The models are able to describe the currents in terms of interpretable local regimes of two–three classes. Scoring rules are used to measure predictive performance of the two cylindrical densities. Results indicate that there is clearly skew angular components, and possibly also some heavy tails in magnitude. publishedVersion This is an open access article distributed under the terms of the Creative Commons CC-BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
format |
Article in Journal/Newspaper |
author |
Lie, Henrik Syversveen Eidsvik, Jo |
spellingShingle |
Lie, Henrik Syversveen Eidsvik, Jo Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
author_facet |
Lie, Henrik Syversveen Eidsvik, Jo |
author_sort |
Lie, Henrik Syversveen |
title |
Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
title_short |
Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
title_full |
Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
title_fullStr |
Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
title_full_unstemmed |
Inference in cylindrical models having latent Markovian classes - with an application to ocean current data |
title_sort |
inference in cylindrical models having latent markovian classes - with an application to ocean current data |
publisher |
Elsevier Science |
publishDate |
2021 |
url |
https://hdl.handle.net/11250/2737939 https://doi.org/10.1016/j.spasta.2021.100497 |
geographic |
Norwegian Sea |
geographic_facet |
Norwegian Sea |
genre |
Norwegian Sea |
genre_facet |
Norwegian Sea |
op_source |
41 Spatial Statistics 100497 |
op_relation |
Norges forskningsråd: 305445 Spatial Statistics. 2021, 41, . urn:issn:2211-6753 https://hdl.handle.net/11250/2737939 https://doi.org/10.1016/j.spasta.2021.100497 cristin:1903533 |
op_rights |
Navngivelse 4.0 Internasjonal http://creativecommons.org/licenses/by/4.0/deed.no |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.1016/j.spasta.2021.100497 |
container_title |
Spatial Statistics |
container_volume |
41 |
container_start_page |
100497 |
_version_ |
1766151419370405888 |