KOPRI Repository

Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection

Cited 32 time in wos
Cited 47 time in scopus

Full metadata record

DC Field Value Language
dc.contributor.authorSanggyun Lee-
dc.contributor.authorLindi J. Quackenbush-
dc.contributor.authorKim, Hyun-cheol-
dc.contributor.authorMinso Shin-
dc.contributor.authorMiae Kim-
dc.contributor.authorJinwoo Kim-
dc.contributor.authorJungho Im-
dc.date.accessioned2018-03-29T06:13:11Z-
dc.date.available2018-03-29T06:13:11Z-
dc.date.issued2016-
dc.identifier.urihttps://repository.kopri.re.kr/handle/201206/7478-
dc.description.abstractSatellite altimeters have been used to monitor Arctic sea ice thickness since the early 2000s. In order to estimate sea ice thickness from satellite altimeter data, leads (i.e., cracks between ice floes) should first be identified for the calculation of sea ice freeboard. In this study, we proposed novel approaches for lead detection using two machine learning algorithms: decision trees and random forest. CryoSat-2 satellite data collected in March and April of 2011?2014 over the Arctic region were used to extract waveform parameters that show the characteristics of leads, ice floes and ocean, including stack standard deviation, stack skewness, stack kurtosis, pulse peakiness and backscatter sigma-0. The parameters were used to identify leads in the machine learning models. Results show that the proposed approaches, with overall accuracy >90%, produced much better performance than existing lead detection methods based on simple thresholding approaches. Sea ice thickness estimated based on the machine learning-detected leads was compared to the averaged Airborne Electromagnetic (AEM)-bird data collected over two days during the CryoSat Validation experiment (CryoVex) field campaign in April 2011. This comparison showed that the proposed machine learning methods had better performance (up to r = 0.83 and Root Mean Square Error (RMSE) = 0.29 m) compared to thickness estimation based on existing lead detection methods (RMSE = 0.86?0.93 m). Sea ice thickness based on the machine learning approaches showed a consistent decline from 2011?2013 and rebounded in 2014.-
dc.languageEnglish-
dc.titleArctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection-
dc.typeArticle-
dc.identifier.bibliographicCitationSanggyun Lee, et al. 2016. "Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection". <em>REMOTE SENSING</em>, 8(1): 698-717.-
dc.citation.titleREMOTE SENSING-
dc.citation.volume8-
dc.citation.number1-
dc.identifier.doi10.3390/rs8090698-
dc.citation.startPage698-
dc.citation.endPage717-
dc.description.articleClassificationSCIE-
dc.description.jcrRateJCR 2014:17.857-
dc.subject.keywordCryoSat-2-
dc.subject.keywordlead detection-
dc.subject.keywordmachine learning-
dc.subject.keywordsea ice thickness-
dc.identifier.localId2016-0144-
dc.identifier.scopusid2-s2.0-85000352309-
dc.identifier.wosid000385488000008-
Appears in Collections  
2014-2016, SaTellite Remote Sensing on West Antarctic Ocean Research (STAR) (14-16) / Kim; Hyun-cheol (PE14040; PE15040; PE16040)
Files in This Item

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse