Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans
We present a Bayesian image classification scheme for discriminating cloud, clear and sea-ice observations at high latitudes to improve identification of areas of clear-sky over ice-free ocean for SST retrieval. We validate the image classification against a manually classified dataset using Advance...
Published in: | Remote Sensing of Environment |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Elsevier
2015
|
Subjects: | |
Online Access: | https://centaur.reading.ac.uk/36200/ |
id |
ftunivreading:oai:centaur.reading.ac.uk:36200 |
---|---|
record_format |
openpolar |
spelling |
ftunivreading:oai:centaur.reading.ac.uk:36200 2024-06-23T07:56:41+00:00 Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans Bulgin, Claire E. Eastwood, Steinar Embury, Owen Merchant, Christopher J. Donlon, Craig 2015-06-01 https://centaur.reading.ac.uk/36200/ unknown Elsevier Bulgin, C. E. <https://centaur.reading.ac.uk/view/creators/90005720.html>, Eastwood, S., Embury, O. <https://centaur.reading.ac.uk/view/creators/90005381.html> orcid:0000-0002-1661-7828 , Merchant, C. J. <https://centaur.reading.ac.uk/view/creators/90005270.html> orcid:0000-0003-4687-9850 and Donlon, C. (2015) Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans. Remote Sensing of Environment, 162. pp. 396-407. ISSN 0034-4257 doi: https://doi.org/10.1016/j.rse.2013.11.022 <https://doi.org/10.1016/j.rse.2013.11.022> Article PeerReviewed 2015 ftunivreading https://doi.org/10.1016/j.rse.2013.11.022 2024-06-11T15:01:09Z We present a Bayesian image classification scheme for discriminating cloud, clear and sea-ice observations at high latitudes to improve identification of areas of clear-sky over ice-free ocean for SST retrieval. We validate the image classification against a manually classified dataset using Advanced Along Track Scanning Radiometer (AATSR) data. A three way classification scheme using a near-infrared textural feature improves classifier accuracy by 9.9 % over the nadir only version of the cloud clearing used in the ATSR Reprocessing for Climate (ARC) project in high latitude regions. The three way classification gives similar numbers of cloud and ice scenes misclassified as clear but significantly more clear-sky cases are correctly identified (89.9 % compared with 65 % for ARC). We also demonstrate the poetential of a Bayesian image classifier including information from the 0.6 micron channel to be used in sea-ice extent and ice surface temperature retrieval with 77.7 % of ice scenes correctly identified and an overall classifier accuracy of 96 %. Article in Journal/Newspaper Sea ice CentAUR: Central Archive at the University of Reading Remote Sensing of Environment 162 396 407 |
institution |
Open Polar |
collection |
CentAUR: Central Archive at the University of Reading |
op_collection_id |
ftunivreading |
language |
unknown |
description |
We present a Bayesian image classification scheme for discriminating cloud, clear and sea-ice observations at high latitudes to improve identification of areas of clear-sky over ice-free ocean for SST retrieval. We validate the image classification against a manually classified dataset using Advanced Along Track Scanning Radiometer (AATSR) data. A three way classification scheme using a near-infrared textural feature improves classifier accuracy by 9.9 % over the nadir only version of the cloud clearing used in the ATSR Reprocessing for Climate (ARC) project in high latitude regions. The three way classification gives similar numbers of cloud and ice scenes misclassified as clear but significantly more clear-sky cases are correctly identified (89.9 % compared with 65 % for ARC). We also demonstrate the poetential of a Bayesian image classifier including information from the 0.6 micron channel to be used in sea-ice extent and ice surface temperature retrieval with 77.7 % of ice scenes correctly identified and an overall classifier accuracy of 96 %. |
format |
Article in Journal/Newspaper |
author |
Bulgin, Claire E. Eastwood, Steinar Embury, Owen Merchant, Christopher J. Donlon, Craig |
spellingShingle |
Bulgin, Claire E. Eastwood, Steinar Embury, Owen Merchant, Christopher J. Donlon, Craig Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
author_facet |
Bulgin, Claire E. Eastwood, Steinar Embury, Owen Merchant, Christopher J. Donlon, Craig |
author_sort |
Bulgin, Claire E. |
title |
Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
title_short |
Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
title_full |
Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
title_fullStr |
Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
title_full_unstemmed |
Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
title_sort |
sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans |
publisher |
Elsevier |
publishDate |
2015 |
url |
https://centaur.reading.ac.uk/36200/ |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
Bulgin, C. E. <https://centaur.reading.ac.uk/view/creators/90005720.html>, Eastwood, S., Embury, O. <https://centaur.reading.ac.uk/view/creators/90005381.html> orcid:0000-0002-1661-7828 , Merchant, C. J. <https://centaur.reading.ac.uk/view/creators/90005270.html> orcid:0000-0003-4687-9850 and Donlon, C. (2015) Sea surface temperature climate change initiative: alternative image classification algorithms for sea-ice affected oceans. Remote Sensing of Environment, 162. pp. 396-407. ISSN 0034-4257 doi: https://doi.org/10.1016/j.rse.2013.11.022 <https://doi.org/10.1016/j.rse.2013.11.022> |
op_doi |
https://doi.org/10.1016/j.rse.2013.11.022 |
container_title |
Remote Sensing of Environment |
container_volume |
162 |
container_start_page |
396 |
op_container_end_page |
407 |
_version_ |
1802649976673665024 |