Application of a Convolutional Neural Network for the Detection of Sea Ice Leads
Despite accounting for a small fraction of the surface area in the Arctic, long and narrow sea ice fractures, known as “leads”, play a critical role in the energy flux between the ocean and atmosphere. As the volume of sea ice in the Arctic has declined over the past few decades, it is increasingly...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13224571 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4571/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4571/ 2023-08-20T04:04:13+02:00 Application of a Convolutional Neural Network for the Detection of Sea Ice Leads Jay P. Hoffman Steven A. Ackerman Yinghui Liu Jeffrey R. Key Iain L. McConnell agris 2021-11-13 application/pdf https://doi.org/10.3390/rs13224571 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs13224571 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 22; Pages: 4571 leads sea ice MODIS VIIRS convolutional neural network U-Net Text 2021 ftmdpi https://doi.org/10.3390/rs13224571 2023-08-01T03:14:42Z Despite accounting for a small fraction of the surface area in the Arctic, long and narrow sea ice fractures, known as “leads”, play a critical role in the energy flux between the ocean and atmosphere. As the volume of sea ice in the Arctic has declined over the past few decades, it is increasingly important to monitor the corresponding changes in sea ice leads. A novel approach has been developed using artificial intelligence (AI) to detect sea ice leads using satellite thermal infrared window data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS). In this new approach, a particular type of convolutional neural network, a U-Net, replaces a series of conventional image processing tests from our legacy algorithm. Results show the new approach has a high detection accuracy with F1 Scores on the order of 0.7. Compared to the legacy algorithm, the new algorithm shows improvement, with more true positives, fewer false positives, fewer false negatives, and better agreement between satellite instruments. Text Arctic Sea ice MDPI Open Access Publishing Arctic Remote Sensing 13 22 4571 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
leads sea ice MODIS VIIRS convolutional neural network U-Net |
spellingShingle |
leads sea ice MODIS VIIRS convolutional neural network U-Net Jay P. Hoffman Steven A. Ackerman Yinghui Liu Jeffrey R. Key Iain L. McConnell Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
topic_facet |
leads sea ice MODIS VIIRS convolutional neural network U-Net |
description |
Despite accounting for a small fraction of the surface area in the Arctic, long and narrow sea ice fractures, known as “leads”, play a critical role in the energy flux between the ocean and atmosphere. As the volume of sea ice in the Arctic has declined over the past few decades, it is increasingly important to monitor the corresponding changes in sea ice leads. A novel approach has been developed using artificial intelligence (AI) to detect sea ice leads using satellite thermal infrared window data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS). In this new approach, a particular type of convolutional neural network, a U-Net, replaces a series of conventional image processing tests from our legacy algorithm. Results show the new approach has a high detection accuracy with F1 Scores on the order of 0.7. Compared to the legacy algorithm, the new algorithm shows improvement, with more true positives, fewer false positives, fewer false negatives, and better agreement between satellite instruments. |
format |
Text |
author |
Jay P. Hoffman Steven A. Ackerman Yinghui Liu Jeffrey R. Key Iain L. McConnell |
author_facet |
Jay P. Hoffman Steven A. Ackerman Yinghui Liu Jeffrey R. Key Iain L. McConnell |
author_sort |
Jay P. Hoffman |
title |
Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
title_short |
Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
title_full |
Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
title_fullStr |
Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
title_full_unstemmed |
Application of a Convolutional Neural Network for the Detection of Sea Ice Leads |
title_sort |
application of a convolutional neural network for the detection of sea ice leads |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13224571 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Remote Sensing; Volume 13; Issue 22; Pages: 4571 |
op_relation |
https://dx.doi.org/10.3390/rs13224571 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13224571 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
22 |
container_start_page |
4571 |
_version_ |
1774714623798280192 |