Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks
Recently, 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, thes...
Published in: | GIScience & Remote Sensing |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Taylor & Francis Group
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1080/15481603.2021.1943213 https://doaj.org/article/d9a6a10dad474ddc9b2c538a3a5a48cd |
id |
ftdoajarticles:oai:doaj.org/article:d9a6a10dad474ddc9b2c538a3a5a48cd |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:d9a6a10dad474ddc9b2c538a3a5a48cd 2023-10-09T21:48:37+02:00 Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks Junhwa Chi Hyun-Cheol Kim 2021-08-01T00:00:00Z https://doi.org/10.1080/15481603.2021.1943213 https://doaj.org/article/d9a6a10dad474ddc9b2c538a3a5a48cd EN eng Taylor & Francis Group http://dx.doi.org/10.1080/15481603.2021.1943213 https://doaj.org/toc/1548-1603 https://doaj.org/toc/1943-7226 1548-1603 1943-7226 doi:10.1080/15481603.2021.1943213 https://doaj.org/article/d9a6a10dad474ddc9b2c538a3a5a48cd GIScience & Remote Sensing, Vol 58, Iss 6, Pp 812-830 (2021) amsr2 arctic sea ice convolutional neural network deep learning passive microwave sea ice thickness Mathematical geography. Cartography GA1-1776 Environmental sciences GE1-350 article 2021 ftdoajarticles https://doi.org/10.1080/15481603.2021.1943213 2023-09-24T00:36:59Z Recently, 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 relationships 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 consistently generated SITs from AMSR2 at 25 km spatial resolution, regardless of time and space. Article in Journal/Newspaper Arctic Global warming Sea ice Directory of Open Access Journals: DOAJ Articles Arctic GIScience & Remote Sensing 58 6 812 830 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
amsr2 arctic sea ice convolutional neural network deep learning passive microwave sea ice thickness Mathematical geography. Cartography GA1-1776 Environmental sciences GE1-350 |
spellingShingle |
amsr2 arctic sea ice convolutional neural network deep learning passive microwave sea ice thickness Mathematical geography. Cartography GA1-1776 Environmental sciences GE1-350 Junhwa Chi Hyun-Cheol Kim Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
topic_facet |
amsr2 arctic sea ice convolutional neural network deep learning passive microwave sea ice thickness Mathematical geography. Cartography GA1-1776 Environmental sciences GE1-350 |
description |
Recently, 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 relationships 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 consistently generated SITs from AMSR2 at 25 km spatial resolution, regardless of time and space. |
format |
Article in Journal/Newspaper |
author |
Junhwa Chi Hyun-Cheol Kim |
author_facet |
Junhwa Chi Hyun-Cheol Kim |
author_sort |
Junhwa Chi |
title |
Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
title_short |
Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
title_full |
Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
title_fullStr |
Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
title_full_unstemmed |
Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks |
title_sort |
retrieval of daily sea ice thickness from amsr2 passive microwave data using ensemble convolutional neural networks |
publisher |
Taylor & Francis Group |
publishDate |
2021 |
url |
https://doi.org/10.1080/15481603.2021.1943213 https://doaj.org/article/d9a6a10dad474ddc9b2c538a3a5a48cd |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Global warming Sea ice |
genre_facet |
Arctic Global warming Sea ice |
op_source |
GIScience & Remote Sensing, Vol 58, Iss 6, Pp 812-830 (2021) |
op_relation |
http://dx.doi.org/10.1080/15481603.2021.1943213 https://doaj.org/toc/1548-1603 https://doaj.org/toc/1943-7226 1548-1603 1943-7226 doi:10.1080/15481603.2021.1943213 https://doaj.org/article/d9a6a10dad474ddc9b2c538a3a5a48cd |
op_doi |
https://doi.org/10.1080/15481603.2021.1943213 |
container_title |
GIScience & Remote Sensing |
container_volume |
58 |
container_issue |
6 |
container_start_page |
812 |
op_container_end_page |
830 |
_version_ |
1779311695542353920 |