Loading…
The 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...
Saved in:
Published in: | Remote sensing of environment 2015-06, Vol.162, p.396-407, Article 396 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653 |
---|---|
cites | cdi_FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653 |
container_end_page | 407 |
container_issue | |
container_start_page | 396 |
container_title | Remote sensing of environment |
container_volume | 162 |
creator | Bulgin, Claire E. Eastwood, Steinar Embury, Owen Merchant, Christopher J. Donlon, Craig |
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 potential of a Bayesian image classifier including information from the 0.6μm 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%.
•Classification in marginal ice zones is critical for sea surface temperature records.•We evaluate algorithms for satellite data image classification at high latitudes.•Clear-cloud-ice classifiers show good water-ice discrimination.•Combining visible and infrared data enhances ice detection. |
doi_str_mv | 10.1016/j.rse.2013.11.022 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1770308853</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0034425713004446</els_id><sourcerecordid>1732807930</sourcerecordid><originalsourceid>FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653</originalsourceid><addsrcrecordid>eNqNkU9v1DAQxS0EEkvhA3DzkUvCTOzECZyqin9SpV7K2Zo4412vsslieytx4bPj7XLiUPU0mtH7zdjvCfEeoUbA7uO-jonrBlDViDU0zQuxwd4MFRjQL8UGQOlKN615Ld6ktAfAtje4EX_udywTk0yn6MmxzHw4cqR8iizdHA6US93RsmUZlpAD5fDAn-T1nDkuj40sou1ZTCkFH1wZroukebvGkHeHJP0azyeqUNaT9-wyT3J1TEt6K155mhO_-1evxM-vX-5vvle3d99-3FzfVk4bnSvsvAIzwMi6oVZ12LfDpFxDbjIMfir_HvWou3Hy1DvfjMPIA3VjVxrUXauuxIfL3mNcf504ZXsIyfE808LrKVk0BhT0faueIVVNXx6joEjxInVxTSmyt8dYzIi_LYI9x2L3tsRiz7FYRFtiKYz5j3EhP1qWI4X5SfLzheRi1EPgaJMLvDieQiye2mkNT9B_AY8Hqls</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1732807930</pqid></control><display><type>article</type><title>The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans</title><source>ScienceDirect Journals</source><creator>Bulgin, Claire E. ; Eastwood, Steinar ; Embury, Owen ; Merchant, Christopher J. ; Donlon, Craig</creator><creatorcontrib>Bulgin, Claire E. ; Eastwood, Steinar ; Embury, Owen ; Merchant, Christopher J. ; Donlon, Craig</creatorcontrib><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 potential of a Bayesian image classifier including information from the 0.6μm 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%.
•Classification in marginal ice zones is critical for sea surface temperature records.•We evaluate algorithms for satellite data image classification at high latitudes.•Clear-cloud-ice classifiers show good water-ice discrimination.•Combining visible and infrared data enhances ice detection.</description><identifier>ISSN: 0034-4257</identifier><identifier>EISSN: 1879-0704</identifier><identifier>DOI: 10.1016/j.rse.2013.11.022</identifier><language>eng</language><publisher>Elsevier Inc</publisher><subject>Bayesian analysis ; Classification ; Classifiers ; Climate change initiative ; Clouds ; High latitudes ; Image classification ; Latitude ; Marine ; Oceans ; Retrieval ; Sea surface temperature</subject><ispartof>Remote sensing of environment, 2015-06, Vol.162, p.396-407, Article 396</ispartof><rights>2014 Elsevier Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653</citedby><cites>FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids></links><search><creatorcontrib>Bulgin, Claire E.</creatorcontrib><creatorcontrib>Eastwood, Steinar</creatorcontrib><creatorcontrib>Embury, Owen</creatorcontrib><creatorcontrib>Merchant, Christopher J.</creatorcontrib><creatorcontrib>Donlon, Craig</creatorcontrib><title>The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans</title><title>Remote sensing of environment</title><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 potential of a Bayesian image classifier including information from the 0.6μm 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%.
•Classification in marginal ice zones is critical for sea surface temperature records.•We evaluate algorithms for satellite data image classification at high latitudes.•Clear-cloud-ice classifiers show good water-ice discrimination.•Combining visible and infrared data enhances ice detection.</description><subject>Bayesian analysis</subject><subject>Classification</subject><subject>Classifiers</subject><subject>Climate change initiative</subject><subject>Clouds</subject><subject>High latitudes</subject><subject>Image classification</subject><subject>Latitude</subject><subject>Marine</subject><subject>Oceans</subject><subject>Retrieval</subject><subject>Sea surface temperature</subject><issn>0034-4257</issn><issn>1879-0704</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNqNkU9v1DAQxS0EEkvhA3DzkUvCTOzECZyqin9SpV7K2Zo4412vsslieytx4bPj7XLiUPU0mtH7zdjvCfEeoUbA7uO-jonrBlDViDU0zQuxwd4MFRjQL8UGQOlKN615Ld6ktAfAtje4EX_udywTk0yn6MmxzHw4cqR8iizdHA6US93RsmUZlpAD5fDAn-T1nDkuj40sou1ZTCkFH1wZroukebvGkHeHJP0azyeqUNaT9-wyT3J1TEt6K155mhO_-1evxM-vX-5vvle3d99-3FzfVk4bnSvsvAIzwMi6oVZ12LfDpFxDbjIMfir_HvWou3Hy1DvfjMPIA3VjVxrUXauuxIfL3mNcf504ZXsIyfE808LrKVk0BhT0faueIVVNXx6joEjxInVxTSmyt8dYzIi_LYI9x2L3tsRiz7FYRFtiKYz5j3EhP1qWI4X5SfLzheRi1EPgaJMLvDieQiye2mkNT9B_AY8Hqls</recordid><startdate>20150601</startdate><enddate>20150601</enddate><creator>Bulgin, Claire E.</creator><creator>Eastwood, Steinar</creator><creator>Embury, Owen</creator><creator>Merchant, Christopher J.</creator><creator>Donlon, Craig</creator><general>Elsevier Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QH</scope><scope>7SN</scope><scope>7ST</scope><scope>7TG</scope><scope>7U6</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>KL.</scope><scope>L.G</scope><scope>SOI</scope><scope>7SU</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>KR7</scope><scope>L7M</scope></search><sort><creationdate>20150601</creationdate><title>The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans</title><author>Bulgin, Claire E. ; Eastwood, Steinar ; Embury, Owen ; Merchant, Christopher J. ; Donlon, Craig</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Bayesian analysis</topic><topic>Classification</topic><topic>Classifiers</topic><topic>Climate change initiative</topic><topic>Clouds</topic><topic>High latitudes</topic><topic>Image classification</topic><topic>Latitude</topic><topic>Marine</topic><topic>Oceans</topic><topic>Retrieval</topic><topic>Sea surface temperature</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bulgin, Claire E.</creatorcontrib><creatorcontrib>Eastwood, Steinar</creatorcontrib><creatorcontrib>Embury, Owen</creatorcontrib><creatorcontrib>Merchant, Christopher J.</creatorcontrib><creatorcontrib>Donlon, Craig</creatorcontrib><collection>CrossRef</collection><collection>Aqualine</collection><collection>Ecology Abstracts</collection><collection>Environment Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Sustainability Science Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><collection>Environment Abstracts</collection><collection>Environmental Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Remote sensing of environment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bulgin, Claire E.</au><au>Eastwood, Steinar</au><au>Embury, Owen</au><au>Merchant, Christopher J.</au><au>Donlon, Craig</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans</atitle><jtitle>Remote sensing of environment</jtitle><date>2015-06-01</date><risdate>2015</risdate><volume>162</volume><spage>396</spage><epage>407</epage><pages>396-407</pages><artnum>396</artnum><issn>0034-4257</issn><eissn>1879-0704</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>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 potential of a Bayesian image classifier including information from the 0.6μm 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%.
•Classification in marginal ice zones is critical for sea surface temperature records.•We evaluate algorithms for satellite data image classification at high latitudes.•Clear-cloud-ice classifiers show good water-ice discrimination.•Combining visible and infrared data enhances ice detection.</abstract><pub>Elsevier Inc</pub><doi>10.1016/j.rse.2013.11.022</doi><tpages>12</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0034-4257 |
ispartof | Remote sensing of environment, 2015-06, Vol.162, p.396-407, Article 396 |
issn | 0034-4257 1879-0704 |
language | eng |
recordid | cdi_proquest_miscellaneous_1770308853 |
source | ScienceDirect Journals |
subjects | Bayesian analysis Classification Classifiers Climate change initiative Clouds High latitudes Image classification Latitude Marine Oceans Retrieval Sea surface temperature |
title | The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T21%3A30%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20sea%20surface%20temperature%20climate%20change%20initiative:%20Alternative%20image%20classification%20algorithms%20for%20sea-ice%20affected%20oceans&rft.jtitle=Remote%20sensing%20of%20environment&rft.au=Bulgin,%20Claire%20E.&rft.date=2015-06-01&rft.volume=162&rft.spage=396&rft.epage=407&rft.pages=396-407&rft.artnum=396&rft.issn=0034-4257&rft.eissn=1879-0704&rft_id=info:doi/10.1016/j.rse.2013.11.022&rft_dat=%3Cproquest_cross%3E1732807930%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c474t-16f30790be42a5361859d3c2acd7e0fd201b4b46bdfa8cf2b9be9a6b68cf14653%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1732807930&rft_id=info:pmid/&rfr_iscdi=true |