Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data
Two effective machine learning-aided sea ice monitoring methods are investigated using 42 months of spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data collected by the TechDemoSat-1 (TDS-1). The two-dimensional delay waveforms with different Doppler spread characteristics are...
Main Authors: | , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://depositonce.tu-berlin.de/handle/11303/12263 https://doi.org/10.14279/depositonce-11139 |
id |
ftdepositonce:oai:depositonce.tu-berlin.de:11303/12263 |
---|---|
record_format |
openpolar |
spelling |
ftdepositonce:oai:depositonce.tu-berlin.de:11303/12263 2023-07-02T03:30:01+02:00 Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data Zhu, Yongchao Tao, Tingye Yu, Kegen Qu, Xiaochuan Li, Shuiping Wickert, Jens Semmling, Maximilian 2020-11-14 application/pdf https://depositonce.tu-berlin.de/handle/11303/12263 https://doi.org/10.14279/depositonce-11139 en eng 2072-4292 https://depositonce.tu-berlin.de/handle/11303/12263 http://dx.doi.org/10.14279/depositonce-11139 https://creativecommons.org/licenses/by/4.0/ 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten Delay-Doppler Map Global Navigation Satellite System-Reflectometry decision tree random forest sea ice monitoring Article publishedVersion 2020 ftdepositonce https://doi.org/10.14279/depositonce-11139 2023-06-12T16:20:05Z Two effective machine learning-aided sea ice monitoring methods are investigated using 42 months of spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data collected by the TechDemoSat-1 (TDS-1). The two-dimensional delay waveforms with different Doppler spread characteristics are applied to extract six features, which are combined to monitor sea ice using the decision tree (DT) and random forest (RF) algorithms. Firstly, the feature sequences are used as input variables and sea ice concentration (SIC) data from the Advanced Microwave Space Radiometer-2 (AMSR-2) are applied as targeted output to train the sea ice monitoring model. Hereafter, the performance of the proposed method is evaluated through comparing with the sea ice edge (SIE) data from the Special Sensor Microwave Imager Sounder (SSMIS) data. The DT- and RF-based methods achieve an overall accuracy of 97.51% and 98.03%, respectively, in the Arctic region and 95.46% and 95.96%, respectively, in the Antarctic region. The DT- and RF-based methods achieve similar accuracies, while the Kappa coefficient of RF-based approach is slightly larger than that of the DT-based approach, which indicates that the RF-based method outperforms the DT-based method. The results show the potential of monitoring sea ice using machine learning-aided GNSS-R approaches. Article in Journal/Newspaper Antarc* Antarctic Arctic Sea ice TU Berlin: Deposit Once Arctic Antarctic The Antarctic |
institution |
Open Polar |
collection |
TU Berlin: Deposit Once |
op_collection_id |
ftdepositonce |
language |
English |
topic |
620 Ingenieurwissenschaften und zugeordnete Tätigkeiten Delay-Doppler Map Global Navigation Satellite System-Reflectometry decision tree random forest sea ice monitoring |
spellingShingle |
620 Ingenieurwissenschaften und zugeordnete Tätigkeiten Delay-Doppler Map Global Navigation Satellite System-Reflectometry decision tree random forest sea ice monitoring Zhu, Yongchao Tao, Tingye Yu, Kegen Qu, Xiaochuan Li, Shuiping Wickert, Jens Semmling, Maximilian Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
topic_facet |
620 Ingenieurwissenschaften und zugeordnete Tätigkeiten Delay-Doppler Map Global Navigation Satellite System-Reflectometry decision tree random forest sea ice monitoring |
description |
Two effective machine learning-aided sea ice monitoring methods are investigated using 42 months of spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data collected by the TechDemoSat-1 (TDS-1). The two-dimensional delay waveforms with different Doppler spread characteristics are applied to extract six features, which are combined to monitor sea ice using the decision tree (DT) and random forest (RF) algorithms. Firstly, the feature sequences are used as input variables and sea ice concentration (SIC) data from the Advanced Microwave Space Radiometer-2 (AMSR-2) are applied as targeted output to train the sea ice monitoring model. Hereafter, the performance of the proposed method is evaluated through comparing with the sea ice edge (SIE) data from the Special Sensor Microwave Imager Sounder (SSMIS) data. The DT- and RF-based methods achieve an overall accuracy of 97.51% and 98.03%, respectively, in the Arctic region and 95.46% and 95.96%, respectively, in the Antarctic region. The DT- and RF-based methods achieve similar accuracies, while the Kappa coefficient of RF-based approach is slightly larger than that of the DT-based approach, which indicates that the RF-based method outperforms the DT-based method. The results show the potential of monitoring sea ice using machine learning-aided GNSS-R approaches. |
format |
Article in Journal/Newspaper |
author |
Zhu, Yongchao Tao, Tingye Yu, Kegen Qu, Xiaochuan Li, Shuiping Wickert, Jens Semmling, Maximilian |
author_facet |
Zhu, Yongchao Tao, Tingye Yu, Kegen Qu, Xiaochuan Li, Shuiping Wickert, Jens Semmling, Maximilian |
author_sort |
Zhu, Yongchao |
title |
Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
title_short |
Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
title_full |
Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
title_fullStr |
Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
title_full_unstemmed |
Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data |
title_sort |
machine learning-aided sea ice monitoring using feature sequences extracted from spaceborne gnss-reflectometry data |
publishDate |
2020 |
url |
https://depositonce.tu-berlin.de/handle/11303/12263 https://doi.org/10.14279/depositonce-11139 |
geographic |
Arctic Antarctic The Antarctic |
geographic_facet |
Arctic Antarctic The Antarctic |
genre |
Antarc* Antarctic Arctic Sea ice |
genre_facet |
Antarc* Antarctic Arctic Sea ice |
op_relation |
2072-4292 https://depositonce.tu-berlin.de/handle/11303/12263 http://dx.doi.org/10.14279/depositonce-11139 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.14279/depositonce-11139 |
_version_ |
1770274287344680960 |