Global surface-ocean partial pressure of carbon dioxide (pCO2) estimates from a machine learning ensemble: CSIR-ML6 v2019a (NCEI Accession 0206205)
This dataset contains surface-ocean partial pressure of carbon dioxide (pCO2) that the ensemble mean of six two-step clustering-regression machine learning methods. The ensemble is a combination of two clustering approaches and three regression methods. For the clustering approaches, we use K-means clustering (21 clusters) and open ocean CO2 biomes as defined by Fay and McKinley (2014). Three machine learning regression methods are applied to each of these two clustering methods. These machine learning methods are feed-forward neural-network (FFN), support vector regression (SVR) and gradient boosted machine using decision trees (GBM). The final estimate of surface ocean pCO2 is the average of the six machine learning estimates resulting in a monthly by 1° ⨉ 1° resolution product that extends from the start of 1982 to the end of 2016. Sea-air fluxes (FCO2) calculated from pCO2 are also presented in the data. The discrete boundaries of the clustering approach result in semi-discrete discontinuities in pCO2 and fCO2 estimates. These are smoothed by applying a 3 ⨉ 3 ⨉ 3 convolution (moving average) to the dataset in time, latitude and longitude.
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | non-public |
| contactPoint |
{
"fn": "NOAA National Centers for Environmental Information",
"@type": "vcard:Contact",
"hasEmail": "mailto:ncei.info@noaa.gov"
}
|
| describedByType | application/octet-steam |
| description | This dataset contains surface-ocean partial pressure of carbon dioxide (pCO2) that the ensemble mean of six two-step clustering-regression machine learning methods. The ensemble is a combination of two clustering approaches and three regression methods. For the clustering approaches, we use K-means clustering (21 clusters) and open ocean CO2 biomes as defined by Fay and McKinley (2014). Three machine learning regression methods are applied to each of these two clustering methods. These machine learning methods are feed-forward neural-network (FFN), support vector regression (SVR) and gradient boosted machine using decision trees (GBM). The final estimate of surface ocean pCO2 is the average of the six machine learning estimates resulting in a monthly by 1° ⨉ 1° resolution product that extends from the start of 1982 to the end of 2016. Sea-air fluxes (FCO2) calculated from pCO2 are also presented in the data. The discrete boundaries of the clustering approach result in semi-discrete discontinuities in pCO2 and fCO2 estimates. These are smoothed by applying a 3 ⨉ 3 ⨉ 3 convolution (moving average) to the dataset in time, latitude and longitude. |
| distribution |
[
{
"@type": "dcat:Distribution",
"title": "Project Metadata",
"accessURL": "https://www.ncei.noaa.gov/data/oceans/ncei/ocads/metadata/0206205.html",
"description": "Navigate directly to the URL for a descriptive web page with download links.",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "NCEI Dataset Landing Page",
"mediaType": "placeholder/value",
"description": "Navigate directly to the URL for a descriptive web page with download links.",
"downloadURL": "https://doi.org/10.25921/z682-mn47",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "Descriptive Information",
"mediaType": "placeholder/value",
"description": "Navigate directly to the URL for a descriptive web page with download links.",
"downloadURL": "https://www.ncei.noaa.gov/archive/accession/oas/206205",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "HTTPS",
"mediaType": "placeholder/value",
"description": "Navigate directly to the URL for data access and direct download.",
"downloadURL": "https://www.ncei.noaa.gov/archive/accession/download/206205",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "FTP",
"mediaType": "placeholder/value",
"description": "These data are available through the File Transfer Protocol (FTP). FTP is no longer supported by most internet browsers. You may copy and paste the FTP link to the data into an FTP client (e.g., FileZilla or WinSCP).",
"downloadURL": "ftp://ftp-oceans.ncei.noaa.gov/nodc/archive/arc0148/0206205/",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "https://doi.org/10.5194/gmd-2019-46",
"mediaType": "placeholder/value",
"description": "related resource",
"downloadURL": "https://doi.org/10.5194/gmd-2019-46",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "https://www.ncei.noaa.gov/access/ocean-carbon-acidification-data-system/oceans/ndp_101/ndp101.html",
"accessURL": "https://www.ncei.noaa.gov/access/ocean-carbon-acidification-data-system/oceans/ndp_101/ndp101.html",
"description": "related resource",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "https://www.ncei.noaa.gov/products/ocean-carbon-acidification-data-system",
"mediaType": "placeholder/value",
"description": "OCADS website",
"downloadURL": "https://www.ncei.noaa.gov/products/ocean-carbon-acidification-data-system",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "GCMD Keyword Forum Page",
"mediaType": "placeholder/value",
"description": "Global Change Master Directory (GCMD). 2025. GCMD Keywords, Version 21. Greenbelt, MD: Earth Science Data and Information System, Earth Science Projects Division, Goddard Space Flight Center (GSFC), National Aeronautics and Space Administration (NASA). URL (GCMD Keyword Forum Page): https://forum.earthdata.nasa.gov/app.php/tag/GCMD+Keywords",
"downloadURL": "https://forum.earthdata.nasa.gov/app.php/tag/GCMD%2BKeywords",
"describedByType": "application/octet-steam"
},
{
"@type": "dcat:Distribution",
"title": "NCEI Contact Information",
"mediaType": "placeholder/value",
"description": "Information for contacts at NCEI.",
"downloadURL": "https://www.ncei.noaa.gov/contact",
"describedByType": "application/octet-steam"
}
]
|
| identifier | gov.noaa.nodc:0206205 |
| issued | 2019-10-31T00:00:00.000+00:00 |
| keyword |
[
"0206205",
"AIR-SEA FLUX - PARTIAL PRESSURE (OR FUGACITY) OF CARBON DIOXIDE",
"partial pressure of carbon dioxide - water",
"pCO2 - AIR",
"showerhead equilibrator",
"chemical",
"meteorological",
"surface measurements",
"VARIOUS CHARTERED VESSELS",
"Council for Scientific and Industrial Research",
"Institute of Biogeochemistry and Pollutant Dynamics",
"Council for Scientific and Industrial Research",
"Surface Ocean CO2 Atlas (SOCAT)",
"Arctic Ocean",
"Indian Ocean",
"North Atlantic Ocean",
"North Pacific Ocean",
"South Atlantic Ocean",
"South Pacific Ocean",
"Southern Ocean",
"oceanography",
"Various",
"Ocean Carbon and Acidification Data System (OCADS) Project",
"EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC CHEMISTRY > CARBON AND HYDROCARBON COMPOUNDS > ATMOSPHERIC CARBON DIOXIDE > PARTIAL PRESSURE OF CARBON DIOXIDE",
"EARTH SCIENCE > OCEANS > OCEAN CHEMISTRY > CARBON DIOXIDE",
"Data synthesis product",
"Discrete measurement",
"Profile",
"FCO2_raw (time, lat, lon)",
"FCO2_smooth (time, lat, lon)",
"Time",
"lat (180)",
"lon (360)",
"pCO2air (time, lat, lon)",
"pCO2sea_raw (time, lat, lon)",
"pCO2sea_smooth (time, lat, lon)",
"seamask (lat, lon)",
"EQUILIBRATORS",
"OCEAN > ARCTIC OCEAN",
"OCEAN > ATLANTIC OCEAN > NORTH ATLANTIC OCEAN",
"OCEAN > ATLANTIC OCEAN > SOUTH ATLANTIC OCEAN",
"OCEAN > INDIAN OCEAN",
"OCEAN > PACIFIC OCEAN > NORTH PACIFIC OCEAN",
"OCEAN > PACIFIC OCEAN > SOUTH PACIFIC OCEAN",
"OCEAN > SOUTHERN OCEAN",
"Arctic Ocean",
"Atlantic Ocean",
"Indian Ocean",
"Pacific Ocean",
"Southern Ocean"
]
|
| landingPage | https://www.ncei.noaa.gov/contact |
| language |
[]
|
| license | https://creativecommons.org/publicdomain/zero/1.0/ |
| modified | 2019-11-05T00:00:00.000+00:00 |
| publisher |
{
"name": "NOAA National Centers for Environmental Information",
"@type": "org:Organization"
}
|
| references |
[
"https://doi.org/10.5194/gmd-2019-46",
"https://www.ncei.noaa.gov/access/ocean-carbon-acidification-data-system/oceans/ndp_101/ndp101.html",
"https://www.ncei.noaa.gov/products/ocean-carbon-acidification-data-system"
]
|
| rights | otherRestrictions |
| spatial | 180.0,-89.5,-180.0,89.5 |
| temporal | 1982-01-01T00:00:00+00:00/2016-12-31T00:00:00+00:00 |
| title | Global surface-ocean partial pressure of carbon dioxide (pCO2) estimates from a machine learning ensemble: CSIR-ML6 v2019a (NCEI Accession 0206205) |
