KOPRI Repository

Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks

Cited 3 time in wos
Cited 3 time in scopus

Full metadata record

DC Field Value Language
dc.contributor.authorChi, Junhwa-
dc.contributor.authorKim, Hyun-Cheol-
dc.date.accessioned2022-07-08T04:25:41Z-
dc.date.available2022-07-08T04:25:41Z-
dc.date.issued2021-08-18-
dc.identifier.urihttps://repository.kopri.re.kr/handle/201206/13649-
dc.description.abstractRecently, measurement of sea ice thickness (SIT) has received increasing attention due to the importance of thinning ice in the context of global warming. Although altimeter sensors onboard satellite missions enable continuous SIT measurements over larger areas compared to in situ observations, these sensors are inadequate for mapping daily Arctic SIT because of their small footprints. We exploited passive microwave data from AMSR2 (Advanced Microwave Scanning Radiometer 2) by incorporating a state-of-the-art deep learning (DL) approach to address this limitation. Passive microwave data offer better temporal resolutions than those from a single altimeter sensors, but are rarely used for SIT estimations due to their limited physical relationship with SIT. In this study, we proposed an ensemble DL model with different modalities to produce daily pan-Arctic SIT retrievals. The proposed model determined the hidden and unknown relation- ships between the brightness temperatures of AMSR2 channels and SITs measured by CryoSat-2 (CS2) from the extended input features defined by our feature augmentation strategy. Although AMSR2-based SITs agreed well with CS2-derived gridded SIT values, they had similar uncertainties and errors in the CS2 SIT measurements, particularly for thin ice. However, based on quantitative validations using long-term unseen data and IceBridge data, the proposed retrieval model con- sistently generated SITs from AMSR2 at 25 km spatial resolution, regardless of time and space.en_US
dc.languageEnglishen_US
dc.language.isoenen_US
dc.subjectPhysical Geographyen_US
dc.subjectRemote Sensingen_US
dc.subject.classification해당사항없음en_US
dc.titleRetrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networksen_US
dc.title.alternativeAMSR2 수동마이크로 기반 일간 북극 해빙두께 산출 인공지능 모델 개발 연구en_US
dc.typeArticleen_US
dc.identifier.bibliographicCitationChi, Junhwa, Kim, Hyun-Cheol. 2021. "Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks". <em>GISCIENCE & REMOTE SENSING</em>, 58(6): 812-830.-
dc.citation.titleGISCIENCE & REMOTE SENSINGen_US
dc.citation.volume58en_US
dc.citation.number6en_US
dc.identifier.doi10.1080/15481603.2021.1943213-
dc.citation.startPage812en_US
dc.citation.endPage830en_US
dc.description.articleClassificationSCIE-
dc.description.jcrRateJCR 2019:6en_US
dc.subject.keywordAMSR2en_US
dc.subject.keywordArctic sea iceen_US
dc.subject.keywordconvolutional neural networken_US
dc.subject.keyworddeep learningen_US
dc.subject.keywordpassive microwaveen_US
dc.subject.keywordsea ice thicknessen_US
dc.identifier.localId2021-0124-
dc.identifier.scopusid2-s2.0-85110742451-
dc.identifier.wosid000673377900001-
Appears in Collections  
2021-2021, Study on remote sensing for quantitative analysis of changes in the Arctic cryosphere (21-21) / Kim, Hyun-cheol (PE21040)
Files in This Item

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

Browse