A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning
Dataset: Distribution of dissolved barium in seawater determined using machine learning We present a spatially and vertically resolved global grid of dissolved barium concentrations ([Ba]) in seawater determined using Gaussian Process Regression machine learning. This model was trained using 4,345 q...
Main Authors: | , |
---|---|
Format: | Dataset |
Language: | English |
Published: |
Biological and Chemical Oceanography Data Management Office (BCO-DMO). Contact: bco-dmo-data@whoi.edu
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/1912/29704 |
id |
ftwhoas:oai:darchive.mblwhoilibrary.org:1912/29704 |
---|---|
record_format |
openpolar |
spelling |
ftwhoas:oai:darchive.mblwhoilibrary.org:1912/29704 2023-05-15T13:42:52+02:00 A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning Horner, Tristan J. Mete, Oyku Z. Eastern Tropical Pacific, Subtropical South Pacific, Sub-Antarctic Pacific, and Southern Oceans westlimit: -179.5; southlimit: -77.5; eastlimit: 179.5; northlimit: 89.5 20070101 - 20181231 (UTC) 2023-02-22 https://hdl.handle.net/1912/29704 en_US eng Biological and Chemical Oceanography Data Management Office (BCO-DMO). Contact: bco-dmo-data@whoi.edu http://lod.bco-dmo.org/id//885506 https://doi.org/10.26008/1912/bco-dmo.885506.1 https://hdl.handle.net/1912/29704 doi:10.26008/1912/bco-dmo.885506.1 Creative Commons Attribution 4.0 https://creativecommons.org/licenses/by/4.0/ CC-BY doi:10.26008/1912/bco-dmo.885506.1 barium barite machine learning Dataset 2023 ftwhoas https://doi.org/10.26008/1912/bco-dmo.885506.1 2023-02-25T23:57:11Z Dataset: Distribution of dissolved barium in seawater determined using machine learning We present a spatially and vertically resolved global grid of dissolved barium concentrations ([Ba]) in seawater determined using Gaussian Process Regression machine learning. This model was trained using 4,345 quality-controlled GEOTRACES data from the Arctic, Atlantic, Pacific, and Southern Oceans. Model output was validated by assessing the accuracy of [Ba] simulations in the Indian Ocean, noting that none of the 1,157 Indian Ocean data were seen by the model during training. We identify a model that can accurate predict [Ba] in the Indian Ocean using six features: depth, temperature, salinity, dissolved oxygen, dissolved phosphate, and dissolved nitrate. This model achieves a mean absolute percentage deviation of 6.3 %. This model was used to simulate [Ba] on a global basis using predictor data from the World Ocean Atlas 2018. The global model of [Ba] is on a 1°x 1° grid with 102 depth levels from 0 to 5,500 m. The dissolved [Ba] output was then used to simulate dissolved Ba* (barium-star), which is the difference between 'observed' and [Ba] predicted from co-located [Si]. Lastly, [Ba] data were combined with temperature, salinity, and pressure data from the World Ocean Atlas to calculate the saturation state of seawater with respect to barite. The model reveals that the volume-weighted mean oceanic [Ba] and and saturation state are 89 nmol kg–1 and 0.82, respectively. These results imply that the total marine Ba inventory is 122±8 ×10¹² mol. For a complete list of measurements, refer to the full dataset description in the supplemental file 'Dataset_description.pdf'. The most current version of this dataset is available at: https://www.bco-dmo.org/dataset/885506 NSF Division of Ocean Sciences (NSF OCE) OCE-2023456, NSF Division of Ocean Sciences (NSF OCE) OCE-2048604 Dataset Antarc* Antarctic Arctic Woods Hole Scientific Community: WHOAS (Woods Hole Open Access Server) Antarctic Arctic Indian Pacific |
institution |
Open Polar |
collection |
Woods Hole Scientific Community: WHOAS (Woods Hole Open Access Server) |
op_collection_id |
ftwhoas |
language |
English |
topic |
barium barite machine learning |
spellingShingle |
barium barite machine learning Horner, Tristan J. Mete, Oyku Z. A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
topic_facet |
barium barite machine learning |
description |
Dataset: Distribution of dissolved barium in seawater determined using machine learning We present a spatially and vertically resolved global grid of dissolved barium concentrations ([Ba]) in seawater determined using Gaussian Process Regression machine learning. This model was trained using 4,345 quality-controlled GEOTRACES data from the Arctic, Atlantic, Pacific, and Southern Oceans. Model output was validated by assessing the accuracy of [Ba] simulations in the Indian Ocean, noting that none of the 1,157 Indian Ocean data were seen by the model during training. We identify a model that can accurate predict [Ba] in the Indian Ocean using six features: depth, temperature, salinity, dissolved oxygen, dissolved phosphate, and dissolved nitrate. This model achieves a mean absolute percentage deviation of 6.3 %. This model was used to simulate [Ba] on a global basis using predictor data from the World Ocean Atlas 2018. The global model of [Ba] is on a 1°x 1° grid with 102 depth levels from 0 to 5,500 m. The dissolved [Ba] output was then used to simulate dissolved Ba* (barium-star), which is the difference between 'observed' and [Ba] predicted from co-located [Si]. Lastly, [Ba] data were combined with temperature, salinity, and pressure data from the World Ocean Atlas to calculate the saturation state of seawater with respect to barite. The model reveals that the volume-weighted mean oceanic [Ba] and and saturation state are 89 nmol kg–1 and 0.82, respectively. These results imply that the total marine Ba inventory is 122±8 ×10¹² mol. For a complete list of measurements, refer to the full dataset description in the supplemental file 'Dataset_description.pdf'. The most current version of this dataset is available at: https://www.bco-dmo.org/dataset/885506 NSF Division of Ocean Sciences (NSF OCE) OCE-2023456, NSF Division of Ocean Sciences (NSF OCE) OCE-2048604 |
format |
Dataset |
author |
Horner, Tristan J. Mete, Oyku Z. |
author_facet |
Horner, Tristan J. Mete, Oyku Z. |
author_sort |
Horner, Tristan J. |
title |
A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
title_short |
A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
title_full |
A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
title_fullStr |
A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
title_full_unstemmed |
A spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using Gaussian Process Regression machine learning |
title_sort |
spatially and vertically resolved global grid of dissolved barium concentrations in seawater determined using gaussian process regression machine learning |
publisher |
Biological and Chemical Oceanography Data Management Office (BCO-DMO). Contact: bco-dmo-data@whoi.edu |
publishDate |
2023 |
url |
https://hdl.handle.net/1912/29704 |
op_coverage |
Eastern Tropical Pacific, Subtropical South Pacific, Sub-Antarctic Pacific, and Southern Oceans westlimit: -179.5; southlimit: -77.5; eastlimit: 179.5; northlimit: 89.5 20070101 - 20181231 (UTC) |
geographic |
Antarctic Arctic Indian Pacific |
geographic_facet |
Antarctic Arctic Indian Pacific |
genre |
Antarc* Antarctic Arctic |
genre_facet |
Antarc* Antarctic Arctic |
op_source |
doi:10.26008/1912/bco-dmo.885506.1 |
op_relation |
http://lod.bco-dmo.org/id//885506 https://doi.org/10.26008/1912/bco-dmo.885506.1 https://hdl.handle.net/1912/29704 doi:10.26008/1912/bco-dmo.885506.1 |
op_rights |
Creative Commons Attribution 4.0 https://creativecommons.org/licenses/by/4.0/ |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.26008/1912/bco-dmo.885506.1 |
_version_ |
1766173777454956544 |