Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods

Satellite-retrieved sea-surface skin temperature (<i>SST<sub>skin</sub></i>) is essential for many Near-Real-Time studies. This study aimed to assess the potential to improve the accuracy of satellite-based <i>SST<sub>skin</sub></i> retrieval in the Ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingkun Luo, Peter J. Minnett, Chong Jia
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4555
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260993471414272
author Bingkun Luo
Peter J. Minnett
Chong Jia
author_facet Bingkun Luo
Peter J. Minnett
Chong Jia
author_sort Bingkun Luo
collection DOAJ
description Satellite-retrieved sea-surface skin temperature (<i>SST<sub>skin</sub></i>) is essential for many Near-Real-Time studies. This study aimed to assess the potential to improve the accuracy of satellite-based <i>SST<sub>skin</sub></i> retrieval in the Caribbean region by using atmospheric correction algorithms based on four readily available machine learning (ML) approaches: eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Random Forest (RF), and the Artificial Neural Network (ANN). The ML models were trained on an extensive dataset comprising in situ SST measurements and atmospheric state parameters obtained from satellite products, reanalyzed datasets, research cruises, surface moorings, and drifting buoys. The benefits and shortcomings of various ML methods were assessed through comparisons with withheld in situ measurements. The results demonstrate that the ML-based algorithms achieve promising accuracy, with mean biases within 0.07 K when compared with the buoy data and ranging from −0.107 K to 0.179 K relative to the ship-derived <i>SST<sub>skin</sub></i> data. Notably, both XGBoost and RF stand out for their superior correlation and efficacy in the statistical results of validation. The improved <i>SST<sub>skin</sub></i> derived using the ML-based algorithms could enhance our understanding of vital oceanic and atmospheric characteristics and have the potential to reduce uncertainty in oceanographic, meteorological, and climate research.
format Article
id doaj-art-e27319c099bf4922bcd4215bb231bb99
institution OA Journals
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e27319c099bf4922bcd4215bb231bb992025-08-20T01:55:31ZengMDPI AGRemote Sensing2072-42922024-12-011623455510.3390/rs16234555Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning MethodsBingkun Luo0Peter J. Minnett1Chong Jia2Harvard–Smithsonian Center for Astrophysics, 60 Garden Street, Cambridge, MA 02138, USADepartment of Ocean Sciences, Rosenstiel School of Marine, Atmospheric, and Earth Science, University of Miami, 4600 Rickenbacker Causeway, Miami, FL 33149, USADepartment of Ocean Sciences, Rosenstiel School of Marine, Atmospheric, and Earth Science, University of Miami, 4600 Rickenbacker Causeway, Miami, FL 33149, USASatellite-retrieved sea-surface skin temperature (<i>SST<sub>skin</sub></i>) is essential for many Near-Real-Time studies. This study aimed to assess the potential to improve the accuracy of satellite-based <i>SST<sub>skin</sub></i> retrieval in the Caribbean region by using atmospheric correction algorithms based on four readily available machine learning (ML) approaches: eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Random Forest (RF), and the Artificial Neural Network (ANN). The ML models were trained on an extensive dataset comprising in situ SST measurements and atmospheric state parameters obtained from satellite products, reanalyzed datasets, research cruises, surface moorings, and drifting buoys. The benefits and shortcomings of various ML methods were assessed through comparisons with withheld in situ measurements. The results demonstrate that the ML-based algorithms achieve promising accuracy, with mean biases within 0.07 K when compared with the buoy data and ranging from −0.107 K to 0.179 K relative to the ship-derived <i>SST<sub>skin</sub></i> data. Notably, both XGBoost and RF stand out for their superior correlation and efficacy in the statistical results of validation. The improved <i>SST<sub>skin</sub></i> derived using the ML-based algorithms could enhance our understanding of vital oceanic and atmospheric characteristics and have the potential to reduce uncertainty in oceanographic, meteorological, and climate research.https://www.mdpi.com/2072-4292/16/23/4555sea surface skin temperatureatmospheric correction algorithmsmachine learning
spellingShingle Bingkun Luo
Peter J. Minnett
Chong Jia
Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
Remote Sensing
sea surface skin temperature
atmospheric correction algorithms
machine learning
title Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
title_full Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
title_fullStr Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
title_full_unstemmed Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
title_short Improving Atmospheric Correction Algorithms for Sea Surface Skin Temperature Retrievals from Moderate-Resolution Imaging Spectroradiometer Using Machine Learning Methods
title_sort improving atmospheric correction algorithms for sea surface skin temperature retrievals from moderate resolution imaging spectroradiometer using machine learning methods
topic sea surface skin temperature
atmospheric correction algorithms
machine learning
url https://www.mdpi.com/2072-4292/16/23/4555
work_keys_str_mv AT bingkunluo improvingatmosphericcorrectionalgorithmsforseasurfaceskintemperatureretrievalsfrommoderateresolutionimagingspectroradiometerusingmachinelearningmethods
AT peterjminnett improvingatmosphericcorrectionalgorithmsforseasurfaceskintemperatureretrievalsfrommoderateresolutionimagingspectroradiometerusingmachinelearningmethods
AT chongjia improvingatmosphericcorrectionalgorithmsforseasurfaceskintemperatureretrievalsfrommoderateresolutionimagingspectroradiometerusingmachinelearningmethods