Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach
Sea surface salinity (SSS) observed by satellite has been widely used since the successful launch of the first salinity satellite in 2009. However, compared with other oceanographic satellite products (e.g., sea surface temperature, SST) that became operational in the 1980s, the SSS product is less...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2024
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs16163084 https://doaj.org/article/88fdbad1f5b34f7ca3990e6208ac0c9e |
id |
ftdoajarticles:oai:doaj.org/article:88fdbad1f5b34f7ca3990e6208ac0c9e |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:88fdbad1f5b34f7ca3990e6208ac0c9e 2024-09-30T14:43:12+00:00 Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach Yating Ouyang Yuhong Zhang Ming Feng Fabio Boschetti Yan Du 2024-08-01T00:00:00Z https://doi.org/10.3390/rs16163084 https://doaj.org/article/88fdbad1f5b34f7ca3990e6208ac0c9e EN eng MDPI AG https://www.mdpi.com/2072-4292/16/16/3084 https://doaj.org/toc/2072-4292 doi:10.3390/rs16163084 2072-4292 https://doaj.org/article/88fdbad1f5b34f7ca3990e6208ac0c9e Remote Sensing, Vol 16, Iss 16, p 3084 (2024) sea surface salinity SMAP Gaussian Mixture Model Science Q article 2024 ftdoajarticles https://doi.org/10.3390/rs16163084 2024-09-02T15:34:37Z Sea surface salinity (SSS) observed by satellite has been widely used since the successful launch of the first salinity satellite in 2009. However, compared with other oceanographic satellite products (e.g., sea surface temperature, SST) that became operational in the 1980s, the SSS product is less mature and lacks effective validation from the user end. We employed an unsupervised machine learning approach to classify the Level 3 SSS bias from the Soil Moisture Active Passive (SMAP) satellite and its observing environment. The classification model divides the samples into fifteen classes based on four variables: satellite SSS bias, SST, rain rate, and wind speed. SST is one of the most significant factors influencing the classification. In regions with cold SST, satellite SSS has an accuracy of less than 0.2 PSU (Practical Salinity Unit), mainly due to the higher uncertainty in the cold environment. A small number of observations near the seawater freezing point show a significant fresh bias caused by sea ice. A systematic bias of the SMAP SSS product is found in the mid-latitudes: positive bias tends to occur north (south) of 45°N(S) and negative bias is more common in 25°N(S)–45°N(S) bands, likely associated with the SMAP calibration scheme. A significant bias also occurs in regions with strong ocean currents and eddy activities, likely due to spatial mismatch in the highly dynamic background. Notably, satellite SSS and in situ data correlations remain good in similar environments with weaker ocean dynamic activities, implying that satellite salinity data are reliable in dynamically active regions for capturing high-resolution details. The features of the SMAP SSS shown in this work call for careful consideration by the data user community when interpreting biased values. Article in Journal/Newspaper Sea ice Directory of Open Access Journals: DOAJ Articles Remote Sensing 16 16 3084 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
sea surface salinity SMAP Gaussian Mixture Model Science Q |
spellingShingle |
sea surface salinity SMAP Gaussian Mixture Model Science Q Yating Ouyang Yuhong Zhang Ming Feng Fabio Boschetti Yan Du Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
topic_facet |
sea surface salinity SMAP Gaussian Mixture Model Science Q |
description |
Sea surface salinity (SSS) observed by satellite has been widely used since the successful launch of the first salinity satellite in 2009. However, compared with other oceanographic satellite products (e.g., sea surface temperature, SST) that became operational in the 1980s, the SSS product is less mature and lacks effective validation from the user end. We employed an unsupervised machine learning approach to classify the Level 3 SSS bias from the Soil Moisture Active Passive (SMAP) satellite and its observing environment. The classification model divides the samples into fifteen classes based on four variables: satellite SSS bias, SST, rain rate, and wind speed. SST is one of the most significant factors influencing the classification. In regions with cold SST, satellite SSS has an accuracy of less than 0.2 PSU (Practical Salinity Unit), mainly due to the higher uncertainty in the cold environment. A small number of observations near the seawater freezing point show a significant fresh bias caused by sea ice. A systematic bias of the SMAP SSS product is found in the mid-latitudes: positive bias tends to occur north (south) of 45°N(S) and negative bias is more common in 25°N(S)–45°N(S) bands, likely associated with the SMAP calibration scheme. A significant bias also occurs in regions with strong ocean currents and eddy activities, likely due to spatial mismatch in the highly dynamic background. Notably, satellite SSS and in situ data correlations remain good in similar environments with weaker ocean dynamic activities, implying that satellite salinity data are reliable in dynamically active regions for capturing high-resolution details. The features of the SMAP SSS shown in this work call for careful consideration by the data user community when interpreting biased values. |
format |
Article in Journal/Newspaper |
author |
Yating Ouyang Yuhong Zhang Ming Feng Fabio Boschetti Yan Du |
author_facet |
Yating Ouyang Yuhong Zhang Ming Feng Fabio Boschetti Yan Du |
author_sort |
Yating Ouyang |
title |
Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
title_short |
Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
title_full |
Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
title_fullStr |
Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
title_full_unstemmed |
Geoclimatic Distribution of Satellite-Observed Salinity Bias Classified by Machine Learning Approach |
title_sort |
geoclimatic distribution of satellite-observed salinity bias classified by machine learning approach |
publisher |
MDPI AG |
publishDate |
2024 |
url |
https://doi.org/10.3390/rs16163084 https://doaj.org/article/88fdbad1f5b34f7ca3990e6208ac0c9e |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Remote Sensing, Vol 16, Iss 16, p 3084 (2024) |
op_relation |
https://www.mdpi.com/2072-4292/16/16/3084 https://doaj.org/toc/2072-4292 doi:10.3390/rs16163084 2072-4292 https://doaj.org/article/88fdbad1f5b34f7ca3990e6208ac0c9e |
op_doi |
https://doi.org/10.3390/rs16163084 |
container_title |
Remote Sensing |
container_volume |
16 |
container_issue |
16 |
container_start_page |
3084 |
_version_ |
1811645102385266688 |