Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery
The frequent presence of cloud cover in polar regions limits the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) and similar instruments for the investigation and monitoring of sea-ice polynyas compared to passive-microwave-based sensors. The very low thermal contrast between presen...
Published in: | The Cryosphere |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
2021
|
Subjects: | |
Online Access: | https://epic.awi.de/id/eprint/53955/ https://tc.copernicus.org/articles/15/1551/2021/ https://hdl.handle.net/10013/epic.c92c9d5a-a7d5-41a5-8ad4-b8dcae2bfb0c |
id |
ftawi:oai:epic.awi.de:53955 |
---|---|
record_format |
openpolar |
spelling |
ftawi:oai:epic.awi.de:53955 2024-09-15T17:41:10+00:00 Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery Paul, S. Huntemann, M. 2021 https://epic.awi.de/id/eprint/53955/ https://tc.copernicus.org/articles/15/1551/2021/ https://hdl.handle.net/10013/epic.c92c9d5a-a7d5-41a5-8ad4-b8dcae2bfb0c unknown Paul, S. orcid:0000-0002-5136-714X and Huntemann, M. (2021) Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery , The Cryosphere, 15 (3), pp. 1551-1565 . doi:10.5194/tc-15-1551-2021 <https://doi.org/10.5194/tc-15-1551-2021> , hdl:10013/epic.c92c9d5a-a7d5-41a5-8ad4-b8dcae2bfb0c EPIC3The Cryosphere, 15(3), pp. 1551-1565 Article isiRev 2021 ftawi https://doi.org/10.5194/tc-15-1551-2021 2024-06-24T04:26:11Z The frequent presence of cloud cover in polar regions limits the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) and similar instruments for the investigation and monitoring of sea-ice polynyas compared to passive-microwave-based sensors. The very low thermal contrast between present clouds and the sea-ice surface in combination with the lack of available visible and near-infrared channels during polar nighttime results in deficiencies in the MODIS cloud mask and dependent MODIS data products. This leads to frequent misclassifications of (i) present clouds as sea ice or open water (false negative) and (ii) open-water and/or thin-ice areas as clouds (false positive), which results in an underestimation of actual polynya area and subsequently derived information. Here, we present a novel machine-learning-based approach using a deep neural network that is able to reliably discriminate between clouds, sea-ice, and open-water and/or thin-ice areas in a given swath solely from thermal-infrared MODIS channels and derived additional information. Compared to the reference MODIS sea-ice product for the year 2017, our data result in an overall increase of 20 % in annual swath-based coverage for the Brunt Ice Shelf polynya, attributed to an improved cloud-cover discrimination and the reduction of false-positive classifications. At the same time, the mean annual polynya area decreases by 44 % through the reduction of false-negative classifications of warm clouds as thin ice. Additionally, higher spatial coverage results in an overall better subdaily representation of thin-ice conditions that cannot be reconstructed with current state-of-the-art cloud-cover compensation methods. Article in Journal/Newspaper Antarc* Antarctic Brunt Ice Shelf Ice Shelf Sea ice The Cryosphere Alfred Wegener Institute for Polar- and Marine Research (AWI): ePIC (electronic Publication Information Center) The Cryosphere 15 3 1551 1565 |
institution |
Open Polar |
collection |
Alfred Wegener Institute for Polar- and Marine Research (AWI): ePIC (electronic Publication Information Center) |
op_collection_id |
ftawi |
language |
unknown |
description |
The frequent presence of cloud cover in polar regions limits the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) and similar instruments for the investigation and monitoring of sea-ice polynyas compared to passive-microwave-based sensors. The very low thermal contrast between present clouds and the sea-ice surface in combination with the lack of available visible and near-infrared channels during polar nighttime results in deficiencies in the MODIS cloud mask and dependent MODIS data products. This leads to frequent misclassifications of (i) present clouds as sea ice or open water (false negative) and (ii) open-water and/or thin-ice areas as clouds (false positive), which results in an underestimation of actual polynya area and subsequently derived information. Here, we present a novel machine-learning-based approach using a deep neural network that is able to reliably discriminate between clouds, sea-ice, and open-water and/or thin-ice areas in a given swath solely from thermal-infrared MODIS channels and derived additional information. Compared to the reference MODIS sea-ice product for the year 2017, our data result in an overall increase of 20 % in annual swath-based coverage for the Brunt Ice Shelf polynya, attributed to an improved cloud-cover discrimination and the reduction of false-positive classifications. At the same time, the mean annual polynya area decreases by 44 % through the reduction of false-negative classifications of warm clouds as thin ice. Additionally, higher spatial coverage results in an overall better subdaily representation of thin-ice conditions that cannot be reconstructed with current state-of-the-art cloud-cover compensation methods. |
format |
Article in Journal/Newspaper |
author |
Paul, S. Huntemann, M. |
spellingShingle |
Paul, S. Huntemann, M. Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
author_facet |
Paul, S. Huntemann, M. |
author_sort |
Paul, S. |
title |
Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
title_short |
Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
title_full |
Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
title_fullStr |
Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
title_full_unstemmed |
Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery |
title_sort |
improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime antarctic sea ice using modis thermal-infrared imagery |
publishDate |
2021 |
url |
https://epic.awi.de/id/eprint/53955/ https://tc.copernicus.org/articles/15/1551/2021/ https://hdl.handle.net/10013/epic.c92c9d5a-a7d5-41a5-8ad4-b8dcae2bfb0c |
genre |
Antarc* Antarctic Brunt Ice Shelf Ice Shelf Sea ice The Cryosphere |
genre_facet |
Antarc* Antarctic Brunt Ice Shelf Ice Shelf Sea ice The Cryosphere |
op_source |
EPIC3The Cryosphere, 15(3), pp. 1551-1565 |
op_relation |
Paul, S. orcid:0000-0002-5136-714X and Huntemann, M. (2021) Improved machine-learning-based open-water--sea-ice--cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery , The Cryosphere, 15 (3), pp. 1551-1565 . doi:10.5194/tc-15-1551-2021 <https://doi.org/10.5194/tc-15-1551-2021> , hdl:10013/epic.c92c9d5a-a7d5-41a5-8ad4-b8dcae2bfb0c |
op_doi |
https://doi.org/10.5194/tc-15-1551-2021 |
container_title |
The Cryosphere |
container_volume |
15 |
container_issue |
3 |
container_start_page |
1551 |
op_container_end_page |
1565 |
_version_ |
1810487302472859648 |