Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.number | 9 | - |
dc.citation.startPage | 686 | - |
dc.citation.title | REMOTE SENSING | - |
dc.citation.volume | 8 | - |
dc.contributor.author | Lee, Sanggyun | - |
dc.contributor.author | Im, Jungho | - |
dc.contributor.author | Kim, Jinwoo | - |
dc.contributor.author | Kim, Miae | - |
dc.contributor.author | Shin, Minso | - |
dc.contributor.author | Kim, Hyun-cheol | - |
dc.contributor.author | Quackenbush, Lindi J. | - |
dc.date.accessioned | 2023-12-21T23:12:39Z | - |
dc.date.available | 2023-12-21T23:12:39Z | - |
dc.date.created | 2016-12-09 | - |
dc.date.issued | 2016-09 | - |
dc.description.abstract | Satellite 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.identifier.bibliographicCitation | REMOTE SENSING, v.8, no.9, pp.686 | - |
dc.identifier.doi | 10.3390/rs8090698 | - |
dc.identifier.issn | 2072-4292 | - |
dc.identifier.scopusid | 2-s2.0-85000352309 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/20935 | - |
dc.identifier.url | http://www.mdpi.com/2072-4292/8/9/698 | - |
dc.identifier.wosid | 000385488000008 | - |
dc.language | 영어 | - |
dc.publisher | MDPI AG | - |
dc.title | Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection | - |
dc.type | Article | - |
dc.description.isOpenAccess | TRUE | - |
dc.relation.journalWebOfScienceCategory | Remote Sensing | - |
dc.relation.journalResearchArea | Remote Sensing | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | CryoSat-2 | - |
dc.subject.keywordAuthor | lead detection | - |
dc.subject.keywordAuthor | sea ice thickness | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordPlus | LAND-COVER CLASSIFICATION | - |
dc.subject.keywordPlus | SURFACE-TEMPERATURE | - |
dc.subject.keywordPlus | ELEVATION CHANGE | - |
dc.subject.keywordPlus | CLIMATE REGIONS | - |
dc.subject.keywordPlus | RANDOM FORESTS | - |
dc.subject.keywordPlus | LIDAR DATA | - |
dc.subject.keywordPlus | IN-SITU | - |
dc.subject.keywordPlus | OCEAN | - |
dc.subject.keywordPlus | FREEBOARD | - |
dc.subject.keywordPlus | IMAGERY | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.