Multisensor Microwave Sea-Ice Classification
Understanding the polar ice regimes is fundamental to the understanding of global climate and other geophysical processes. Sea ice characteristics can be grouped into a number of .general sea ice classes. Multisensor data from NSCAT, ERS-2, and SSM/I is reconstructed into enhanced resolution imagery...
Main Author: | |
---|---|
Format: | Text |
Language: | unknown |
Published: |
DigitalCommons@USU
1999
|
Subjects: | |
Online Access: | https://digitalcommons.usu.edu/spacegrant/1999/Session2/2 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=1294&context=spacegrant |
id |
ftutahsudc:oai:digitalcommons.usu.edu:spacegrant-1294 |
---|---|
record_format |
openpolar |
spelling |
ftutahsudc:oai:digitalcommons.usu.edu:spacegrant-1294 2023-05-15T18:17:15+02:00 Multisensor Microwave Sea-Ice Classification Remund, Quinn P. 1999-05-10T17:45:00Z application/pdf https://digitalcommons.usu.edu/spacegrant/1999/Session2/2 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=1294&context=spacegrant unknown DigitalCommons@USU https://digitalcommons.usu.edu/spacegrant/1999/Session2/2 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=1294&context=spacegrant Utah Space Grant Consortium text 1999 ftutahsudc 2022-03-07T21:23:13Z Understanding the polar ice regimes is fundamental to the understanding of global climate and other geophysical processes. Sea ice characteristics can be grouped into a number of .general sea ice classes. Multisensor data from NSCAT, ERS-2, and SSM/I is reconstructed into enhanced resolution imagery for use in ice type classification. The resulting 12-dimensional data set is linearly transformed through principal component analysis to reduce data dimensionality and noise levels. An iterative statistical data segmentation algorithm is developed using maximum a pasteriori techniques. The conditional probability distributions of observed vectors given the ice type are assumed to be Gaussian. The cluster centroids, covariance matrices, and a priori ·distributions are estimated from the classification of a previous temporal image set. An initial classification is produced using centroid training data and a weighted nearest neighbor classifier. Though validation is limited, the algorithm results in an ice classi1ication which is subjectively superior to a conventional k-means approach. Text Sea ice Utah State University: DigitalCommons@USU |
institution |
Open Polar |
collection |
Utah State University: DigitalCommons@USU |
op_collection_id |
ftutahsudc |
language |
unknown |
description |
Understanding the polar ice regimes is fundamental to the understanding of global climate and other geophysical processes. Sea ice characteristics can be grouped into a number of .general sea ice classes. Multisensor data from NSCAT, ERS-2, and SSM/I is reconstructed into enhanced resolution imagery for use in ice type classification. The resulting 12-dimensional data set is linearly transformed through principal component analysis to reduce data dimensionality and noise levels. An iterative statistical data segmentation algorithm is developed using maximum a pasteriori techniques. The conditional probability distributions of observed vectors given the ice type are assumed to be Gaussian. The cluster centroids, covariance matrices, and a priori ·distributions are estimated from the classification of a previous temporal image set. An initial classification is produced using centroid training data and a weighted nearest neighbor classifier. Though validation is limited, the algorithm results in an ice classi1ication which is subjectively superior to a conventional k-means approach. |
format |
Text |
author |
Remund, Quinn P. |
spellingShingle |
Remund, Quinn P. Multisensor Microwave Sea-Ice Classification |
author_facet |
Remund, Quinn P. |
author_sort |
Remund, Quinn P. |
title |
Multisensor Microwave Sea-Ice Classification |
title_short |
Multisensor Microwave Sea-Ice Classification |
title_full |
Multisensor Microwave Sea-Ice Classification |
title_fullStr |
Multisensor Microwave Sea-Ice Classification |
title_full_unstemmed |
Multisensor Microwave Sea-Ice Classification |
title_sort |
multisensor microwave sea-ice classification |
publisher |
DigitalCommons@USU |
publishDate |
1999 |
url |
https://digitalcommons.usu.edu/spacegrant/1999/Session2/2 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=1294&context=spacegrant |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Utah Space Grant Consortium |
op_relation |
https://digitalcommons.usu.edu/spacegrant/1999/Session2/2 https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=1294&context=spacegrant |
_version_ |
1766191353133268992 |