1. Home
  2. Organizations
  3. National Oceanic and ...
  4. Global surface-ocean partial ...

Global surface-ocean partial pressure of carbon dioxide (pCO2) estimates from a machine learning ensemble: CSIR-ML6 v2019a (NCEI Accession 0206205)

This NCEI accession 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.

Data and Resources

Additional Info

Field Value
Last Updated November 3, 2019, 21:26
Created November 3, 2019, 21:26
access_constraints ["Cite as: Gregor, Luke; Lebehot, Alice D.; Kok, Schalk; Monteiro, Pedro M. S. (2019). Global surface-ocean partial pressure of carbon dioxide (pCO2) estimates from a machine learning ensemble: CSIR-ML6 v2019a (NCEI Accession 0206205). [indicate subset used]. NOAA National Centers for Environmental Information. Unpublished Dataset. https://accession.nodc.noaa.gov/0206205. Accessed [date].", "Use liability: NOAA and NCEI cannot provide any warranty as to the accuracy, reliability, or completeness of furnished data. Users assume responsibility to determine the usability of these data. The user is responsible for the results of any application of this data for other than its intended purpose."]
bbox-east-long 180
bbox-north-lat 89.5
bbox-south-lat -89.5
bbox-west-long -180
contact-email NCEI.Info@noaa.gov
coupled-resource []
dataset-reference-date [{"type": "publication", "value": "2019-10-31"}]
frequency-of-update asNeeded
graphic-preview-description NOAA logo.
graphic-preview-file https://data.nodc.noaa.gov/cgi-bin/gfx?id=gov.noaa.nodc:0206205
graphic-preview-type PNG
guid gov.noaa.nodc:0206205
licence ["Data in this archival information package are not currently available for public download from NCEI. Please contact NCEI Information Services directly for access to these data.", "accessLevel: Public"]
metadata-date 2019-11-02T05:47:07Z
metadata-language eng
progress pending
resource-type dataset
responsible-party [{"name": "", "roles": ["pointOfContact"]}]
spatial {"type": "Polygon", "coordinates": [[[-180.0, -89.5], [180.0, -89.5], [180.0, 89.5], [-180.0, 89.5], [-180.0, -89.5]]]}
spatial-data-service-type
spatial-reference-system
spatial_harvester true
temporal-extent-begin 1982-01-01
temporal-extent-end 1982-01-01