Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ...
Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) c...
Main Authors: | , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2303.12719 https://arxiv.org/abs/2303.12719 |
id |
ftdatacite:10.48550/arxiv.2303.12719 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2303.12719 2023-05-15T14:13:38+02:00 Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... Iqrah, Jurdana Masuma Koo, Younghyun Wang, Wei Xie, Hongjie Prasad, Sushil 2023 https://dx.doi.org/10.48550/arxiv.2303.12719 https://arxiv.org/abs/2303.12719 unknown arXiv Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering Article article Preprint CreativeWork 2023 ftdatacite https://doi.org/10.48550/arxiv.2303.12719 2023-04-03T16:37:35Z Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) captures high-resolution optical imagery over the polar regions. This research aims at developing a robust and effective system for classifying polar sea ice as thick or snow-covered, young or thin, or open water using S2 images. A key challenge is the lack of labeled S2 training data to serve as the ground truth. We demonstrate a method with high precision to segment and automatically label the S2 images based on suitably determined color thresholds and employ these auto-labeled data to train a U-Net machine model (a fully convolutional neural network), yielding good classification accuracy. Evaluation results over S2 data from the polar summer season in the Ross Sea region of the Antarctic show that the U-Net ... : 2nd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE), February 2023 ... Article in Journal/Newspaper Antarc* Antarctic Ross Sea Sea ice DataCite Metadata Store (German National Library of Science and Technology) Antarctic The Antarctic Ross Sea The Sentinel ENVELOPE(73.317,73.317,-52.983,-52.983) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering Iqrah, Jurdana Masuma Koo, Younghyun Wang, Wei Xie, Hongjie Prasad, Sushil Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Machine Learning cs.LG Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
description |
Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) captures high-resolution optical imagery over the polar regions. This research aims at developing a robust and effective system for classifying polar sea ice as thick or snow-covered, young or thin, or open water using S2 images. A key challenge is the lack of labeled S2 training data to serve as the ground truth. We demonstrate a method with high precision to segment and automatically label the S2 images based on suitably determined color thresholds and employ these auto-labeled data to train a U-Net machine model (a fully convolutional neural network), yielding good classification accuracy. Evaluation results over S2 data from the polar summer season in the Ross Sea region of the Antarctic show that the U-Net ... : 2nd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE), February 2023 ... |
format |
Article in Journal/Newspaper |
author |
Iqrah, Jurdana Masuma Koo, Younghyun Wang, Wei Xie, Hongjie Prasad, Sushil |
author_facet |
Iqrah, Jurdana Masuma Koo, Younghyun Wang, Wei Xie, Hongjie Prasad, Sushil |
author_sort |
Iqrah, Jurdana Masuma |
title |
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
title_short |
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
title_full |
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
title_fullStr |
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
title_full_unstemmed |
Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model ... |
title_sort |
toward polar sea-ice classification using color-based segmentation and auto-labeling of sentinel-2 imagery to train an efficient deep learning model ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2303.12719 https://arxiv.org/abs/2303.12719 |
long_lat |
ENVELOPE(73.317,73.317,-52.983,-52.983) |
geographic |
Antarctic The Antarctic Ross Sea The Sentinel |
geographic_facet |
Antarctic The Antarctic Ross Sea The Sentinel |
genre |
Antarc* Antarctic Ross Sea Sea ice |
genre_facet |
Antarc* Antarctic Ross Sea Sea ice |
op_rights |
Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2303.12719 |
_version_ |
1766286090820386816 |