The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK

Understanding and monitoring sea surface salinity (SSS) and temperature (SST) is vital for assessing ocean health. Interconnections among the ocean, atmosphere, seabed, and land create a complex environment with diverse spatial and temporal scales. Climate change exacerbates marine heatwaves, eutrop...

Full description

Saved in:
Bibliographic Details
Main Authors: Solomon White, Tiago Silva, Laurent O. Amoudry, Evangelos Spyrakos, Adrien Martin, Encarni Medina-Lopez
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Environmental Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenvs.2024.1426547/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850106511928328192
author Solomon White
Tiago Silva
Laurent O. Amoudry
Evangelos Spyrakos
Adrien Martin
Adrien Martin
Encarni Medina-Lopez
author_facet Solomon White
Tiago Silva
Laurent O. Amoudry
Evangelos Spyrakos
Adrien Martin
Adrien Martin
Encarni Medina-Lopez
author_sort Solomon White
collection DOAJ
description Understanding and monitoring sea surface salinity (SSS) and temperature (SST) is vital for assessing ocean health. Interconnections among the ocean, atmosphere, seabed, and land create a complex environment with diverse spatial and temporal scales. Climate change exacerbates marine heatwaves, eutrophication, and acidification, impacting biodiversity and coastal communities. Satellite-derived ocean colour data provides enhanced spatial coverage and resolution compared to traditional methods, enabling the estimation of SST and SSS. This study presents a methodology for extracting SST and SSS using machine learning algorithms trained with in-situ and multispectral satellite data. A global neural network model was developed, leveraging spectral bands and metadata to predict these parameters. The model incorporated Shapley values to evaluate feature importance, offering insight into the contributions of specific bands and environmental factors. The global model achieved an R2 of 0.83 for temperature and 0.65 for salinity. In the Gulf of Mexico case study, the model demonstrated a root mean square error (RMSE) of 0.83°C for test cases and 1.69°C for validation cases for SST, outperforming traditional methods in dynamic coastal environments. Feature importance analysis identified the critical roles of infrared bands in SST prediction and blue/green colour bands in SSS estimation. This approach addresses the “black box” nature of machine learning models by providing insights into the relative importance of spectral bands and metadata. Key factors such as solar azimuth angle and specific spectral bands were highlighted, demonstrating the potential of machine learning to enhance ocean property estimation, particularly in complex coastal regions.
format Article
id doaj-art-75e04d538c8a44d8bc894c0f8ccac96a
institution OA Journals
issn 2296-665X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Environmental Science
spelling doaj-art-75e04d538c8a44d8bc894c0f8ccac96a2025-08-20T02:38:49ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2024-12-011210.3389/fenvs.2024.14265471426547The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UKSolomon White0Tiago Silva1Laurent O. Amoudry2Evangelos Spyrakos3Adrien Martin4Adrien Martin5Encarni Medina-Lopez6Institute for Infrastructure and Environment, School of Engineering, The University of Edinburgh, Edinburgh, United KingdomCentre for Environment, Fisheries and Aquaculture Science (CEFAS), Lowestoft, United KingdomNational Oceanography Centre, Liverpool, United KingdomDepartment of Biological and Environmental Sciences, University of Stirling, Stirling, United KingdomNational Oceanography Centre, Southampton, United KingdomNOVELTIS, Labège, FranceInstitute for Infrastructure and Environment, School of Engineering, The University of Edinburgh, Edinburgh, United KingdomUnderstanding and monitoring sea surface salinity (SSS) and temperature (SST) is vital for assessing ocean health. Interconnections among the ocean, atmosphere, seabed, and land create a complex environment with diverse spatial and temporal scales. Climate change exacerbates marine heatwaves, eutrophication, and acidification, impacting biodiversity and coastal communities. Satellite-derived ocean colour data provides enhanced spatial coverage and resolution compared to traditional methods, enabling the estimation of SST and SSS. This study presents a methodology for extracting SST and SSS using machine learning algorithms trained with in-situ and multispectral satellite data. A global neural network model was developed, leveraging spectral bands and metadata to predict these parameters. The model incorporated Shapley values to evaluate feature importance, offering insight into the contributions of specific bands and environmental factors. The global model achieved an R2 of 0.83 for temperature and 0.65 for salinity. In the Gulf of Mexico case study, the model demonstrated a root mean square error (RMSE) of 0.83°C for test cases and 1.69°C for validation cases for SST, outperforming traditional methods in dynamic coastal environments. Feature importance analysis identified the critical roles of infrared bands in SST prediction and blue/green colour bands in SSS estimation. This approach addresses the “black box” nature of machine learning models by providing insights into the relative importance of spectral bands and metadata. Key factors such as solar azimuth angle and specific spectral bands were highlighted, demonstrating the potential of machine learning to enhance ocean property estimation, particularly in complex coastal regions.https://www.frontiersin.org/articles/10.3389/fenvs.2024.1426547/fullmachine learningsatellite multispectral imagerycoastal oceanographyexplainable AIocean colourtemperature
spellingShingle Solomon White
Tiago Silva
Laurent O. Amoudry
Evangelos Spyrakos
Adrien Martin
Adrien Martin
Encarni Medina-Lopez
The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
Frontiers in Environmental Science
machine learning
satellite multispectral imagery
coastal oceanography
explainable AI
ocean colour
temperature
title The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
title_full The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
title_fullStr The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
title_full_unstemmed The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
title_short The colours of the ocean: using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas, the Gulf of Mexico and the UK
title_sort colours of the ocean using multispectral satellite imagery to estimate sea surface temperature and salinity on global coastal areas the gulf of mexico and the uk
topic machine learning
satellite multispectral imagery
coastal oceanography
explainable AI
ocean colour
temperature
url https://www.frontiersin.org/articles/10.3389/fenvs.2024.1426547/full
work_keys_str_mv AT solomonwhite thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT tiagosilva thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT laurentoamoudry thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT evangelosspyrakos thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT adrienmartin thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT adrienmartin thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT encarnimedinalopez thecoloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT solomonwhite coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT tiagosilva coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT laurentoamoudry coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT evangelosspyrakos coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT adrienmartin coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT adrienmartin coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk
AT encarnimedinalopez coloursoftheoceanusingmultispectralsatelliteimagerytoestimateseasurfacetemperatureandsalinityonglobalcoastalareasthegulfofmexicoandtheuk