Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection
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...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2016
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs8090698 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/8/9/698/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/8/9/698/ 2023-08-20T04:04:08+02:00 Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection Sanggyun Lee Jungho Im Jinwoo Kim Miae Kim Minso Shin Hyun-cheol Kim Lindi Quackenbush agris 2016-08-24 application/pdf https://doi.org/10.3390/rs8090698 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs8090698 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 8; Issue 9; Pages: 698 CryoSat-2 lead detection sea ice thickness machine learning Text 2016 ftmdpi https://doi.org/10.3390/rs8090698 2023-07-31T20:56:24Z 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. Text Arctic CryoSat Validation Experiment Sea ice MDPI Open Access Publishing Arctic Remote Sensing 8 9 698 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
CryoSat-2 lead detection sea ice thickness machine learning |
spellingShingle |
CryoSat-2 lead detection sea ice thickness machine learning Sanggyun Lee Jungho Im Jinwoo Kim Miae Kim Minso Shin Hyun-cheol Kim Lindi Quackenbush Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
topic_facet |
CryoSat-2 lead detection sea ice thickness machine learning |
description |
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. |
format |
Text |
author |
Sanggyun Lee Jungho Im Jinwoo Kim Miae Kim Minso Shin Hyun-cheol Kim Lindi Quackenbush |
author_facet |
Sanggyun Lee Jungho Im Jinwoo Kim Miae Kim Minso Shin Hyun-cheol Kim Lindi Quackenbush |
author_sort |
Sanggyun Lee |
title |
Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
title_short |
Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
title_full |
Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
title_fullStr |
Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
title_full_unstemmed |
Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection |
title_sort |
arctic sea ice thickness estimation from cryosat-2 satellite data using machine learning-based lead detection |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2016 |
url |
https://doi.org/10.3390/rs8090698 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic CryoSat Validation Experiment Sea ice |
genre_facet |
Arctic CryoSat Validation Experiment Sea ice |
op_source |
Remote Sensing; Volume 8; Issue 9; Pages: 698 |
op_relation |
https://dx.doi.org/10.3390/rs8090698 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs8090698 |
container_title |
Remote Sensing |
container_volume |
8 |
container_issue |
9 |
container_start_page |
698 |
_version_ |
1774714549796077568 |