A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks
The ocean's role in modulating the observed 1–7 Pg C yr−1 inter-annual variability in atmospheric CO2 growth rate is an important, but poorly constrained process due to current spatio-temporal limitations in ocean carbon measurements. Here, we investigate and develop a non-linear empirical appr...
Published in: | Biogeosciences |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Gesellschaft Mbh
2013
|
Subjects: | |
Online Access: | https://archimer.ifremer.fr/doc/00661/77335/78774.pdf https://archimer.ifremer.fr/doc/00661/77335/78775.zip https://archimer.ifremer.fr/doc/00661/77335/78776.pdf https://archimer.ifremer.fr/doc/00661/77335/78777.pdf https://doi.org/10.5194/bg-10-4319-2013 https://archimer.ifremer.fr/doc/00661/77335/ |
id |
ftarchimer:oai:archimer.ifremer.fr:77335 |
---|---|
record_format |
openpolar |
spelling |
ftarchimer:oai:archimer.ifremer.fr:77335 2023-05-15T17:37:04+02:00 A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks Sasse, T. P. Mcneil, B. I. Abramowitz, Ag 2013 application/pdf https://archimer.ifremer.fr/doc/00661/77335/78774.pdf https://archimer.ifremer.fr/doc/00661/77335/78775.zip https://archimer.ifremer.fr/doc/00661/77335/78776.pdf https://archimer.ifremer.fr/doc/00661/77335/78777.pdf https://doi.org/10.5194/bg-10-4319-2013 https://archimer.ifremer.fr/doc/00661/77335/ eng eng Copernicus Gesellschaft Mbh https://archimer.ifremer.fr/doc/00661/77335/78774.pdf https://archimer.ifremer.fr/doc/00661/77335/78775.zip https://archimer.ifremer.fr/doc/00661/77335/78776.pdf https://archimer.ifremer.fr/doc/00661/77335/78777.pdf doi:10.5194/bg-10-4319-2013 https://archimer.ifremer.fr/doc/00661/77335/ info:eu-repo/semantics/openAccess restricted use Biogeosciences (1726-4170) (Copernicus Gesellschaft Mbh), 2013 , Vol. 10 , N. 6 , P. 4319-4340 text Publication info:eu-repo/semantics/article 2013 ftarchimer https://doi.org/10.5194/bg-10-4319-2013 2021-09-23T20:36:29Z The ocean's role in modulating the observed 1–7 Pg C yr−1 inter-annual variability in atmospheric CO2 growth rate is an important, but poorly constrained process due to current spatio-temporal limitations in ocean carbon measurements. Here, we investigate and develop a non-linear empirical approach to predict inorganic CO2 concentrations (total carbon dioxide (CT) and total alkalinity (AT)) in the global ocean mixed layer from hydrographic properties (temperature, salinity, dissolved oxygen and nutrients). The benefit of this approach is that once the empirical relationship is established, it can be applied to hydrographic datasets that have better spatio-temporal coverage, and therefore provide an additional constraint to diagnose ocean carbon dynamics globally. Previous empirical approaches have employed multiple linear regressions (MLR) and relied on ad hoc geographic and temporal partitioning of carbon data to constrain complex global carbon dynamics in the mixed layer. Synthesizing a new global CT/AT carbon bottle dataset consisting of ~33 000 measurements in the open ocean mixed layer, we develop a neural network based approach to better constrain the non-linear carbon system. The approach classifies features in the global biogeochemical dataset based on their similarity and homogeneity in a self-organizing map (SOM; Kohonen, 1988). After the initial SOM analysis, which includes geographic constraints, we apply a local linear optimizer to the neural network, which considerably enhances the predictive skill of the new approach. We call this new approach SOMLO, or self-organizing multiple linear output. Using independent bottle carbon data, we compare a traditional MLR analysis to our SOMLO approach to capture the spatial CT and AT distributions. We find the SOMLO approach improves predictive skill globally by 19% for CT, with a global capacity to predict CT to within 10.9 μmol kg−1 (9.2 μmol kg−1 for AT). The non-linear SOMLO approach is particularly powerful in complex but important regions like the Southern Ocean, North Atlantic and equatorial Pacific, where residual standard errors were reduced between 25 and 40% over traditional linear methods. We further test the SOMLO technique using the Bermuda Atlantic time series (BATS) and Hawaiian ocean time series (HOT) datasets, where hydrographic data was capable of explaining 90% of the seasonal cycle and inter-annual variability at those multi-decadal time-series stations. Article in Journal/Newspaper North Atlantic Southern Ocean Archimer (Archive Institutionnelle de l'Ifremer - Institut français de recherche pour l'exploitation de la mer) Pacific Southern Ocean Biogeosciences 10 6 4319 4340 |
institution |
Open Polar |
collection |
Archimer (Archive Institutionnelle de l'Ifremer - Institut français de recherche pour l'exploitation de la mer) |
op_collection_id |
ftarchimer |
language |
English |
description |
The ocean's role in modulating the observed 1–7 Pg C yr−1 inter-annual variability in atmospheric CO2 growth rate is an important, but poorly constrained process due to current spatio-temporal limitations in ocean carbon measurements. Here, we investigate and develop a non-linear empirical approach to predict inorganic CO2 concentrations (total carbon dioxide (CT) and total alkalinity (AT)) in the global ocean mixed layer from hydrographic properties (temperature, salinity, dissolved oxygen and nutrients). The benefit of this approach is that once the empirical relationship is established, it can be applied to hydrographic datasets that have better spatio-temporal coverage, and therefore provide an additional constraint to diagnose ocean carbon dynamics globally. Previous empirical approaches have employed multiple linear regressions (MLR) and relied on ad hoc geographic and temporal partitioning of carbon data to constrain complex global carbon dynamics in the mixed layer. Synthesizing a new global CT/AT carbon bottle dataset consisting of ~33 000 measurements in the open ocean mixed layer, we develop a neural network based approach to better constrain the non-linear carbon system. The approach classifies features in the global biogeochemical dataset based on their similarity and homogeneity in a self-organizing map (SOM; Kohonen, 1988). After the initial SOM analysis, which includes geographic constraints, we apply a local linear optimizer to the neural network, which considerably enhances the predictive skill of the new approach. We call this new approach SOMLO, or self-organizing multiple linear output. Using independent bottle carbon data, we compare a traditional MLR analysis to our SOMLO approach to capture the spatial CT and AT distributions. We find the SOMLO approach improves predictive skill globally by 19% for CT, with a global capacity to predict CT to within 10.9 μmol kg−1 (9.2 μmol kg−1 for AT). The non-linear SOMLO approach is particularly powerful in complex but important regions like the Southern Ocean, North Atlantic and equatorial Pacific, where residual standard errors were reduced between 25 and 40% over traditional linear methods. We further test the SOMLO technique using the Bermuda Atlantic time series (BATS) and Hawaiian ocean time series (HOT) datasets, where hydrographic data was capable of explaining 90% of the seasonal cycle and inter-annual variability at those multi-decadal time-series stations. |
format |
Article in Journal/Newspaper |
author |
Sasse, T. P. Mcneil, B. I. Abramowitz, Ag |
spellingShingle |
Sasse, T. P. Mcneil, B. I. Abramowitz, Ag A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
author_facet |
Sasse, T. P. Mcneil, B. I. Abramowitz, Ag |
author_sort |
Sasse, T. P. |
title |
A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
title_short |
A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
title_full |
A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
title_fullStr |
A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
title_full_unstemmed |
A novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
title_sort |
novel method for diagnosing seasonal to inter-annual surface ocean carbon dynamics from bottle data using neural networks |
publisher |
Copernicus Gesellschaft Mbh |
publishDate |
2013 |
url |
https://archimer.ifremer.fr/doc/00661/77335/78774.pdf https://archimer.ifremer.fr/doc/00661/77335/78775.zip https://archimer.ifremer.fr/doc/00661/77335/78776.pdf https://archimer.ifremer.fr/doc/00661/77335/78777.pdf https://doi.org/10.5194/bg-10-4319-2013 https://archimer.ifremer.fr/doc/00661/77335/ |
geographic |
Pacific Southern Ocean |
geographic_facet |
Pacific Southern Ocean |
genre |
North Atlantic Southern Ocean |
genre_facet |
North Atlantic Southern Ocean |
op_source |
Biogeosciences (1726-4170) (Copernicus Gesellschaft Mbh), 2013 , Vol. 10 , N. 6 , P. 4319-4340 |
op_relation |
https://archimer.ifremer.fr/doc/00661/77335/78774.pdf https://archimer.ifremer.fr/doc/00661/77335/78775.zip https://archimer.ifremer.fr/doc/00661/77335/78776.pdf https://archimer.ifremer.fr/doc/00661/77335/78777.pdf doi:10.5194/bg-10-4319-2013 https://archimer.ifremer.fr/doc/00661/77335/ |
op_rights |
info:eu-repo/semantics/openAccess restricted use |
op_doi |
https://doi.org/10.5194/bg-10-4319-2013 |
container_title |
Biogeosciences |
container_volume |
10 |
container_issue |
6 |
container_start_page |
4319 |
op_container_end_page |
4340 |
_version_ |
1766136790222110720 |