The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean
A feed-forward neural network (FFNN) was used to estimate the monthly climatology of partial pressure of CO 2 ( p CO 2W ) at a spatial resolution of 1° latitude by 1° longitude in the continental shelf of the European Arctic Sector (EAS) of the Arctic Ocean (the Greenland, Norwegian, and Barents sea...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14020312 https://doaj.org/article/a5dd320712af4655904039ea87affc0c |
id |
ftdoajarticles:oai:doaj.org/article:a5dd320712af4655904039ea87affc0c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:a5dd320712af4655904039ea87affc0c 2023-05-15T14:49:55+02:00 The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean Iwona Wrobel-Niedzwiecka Małgorzata Kitowska Przemyslaw Makuch Piotr Markuszewski 2022-01-01T00:00:00Z https://doi.org/10.3390/rs14020312 https://doaj.org/article/a5dd320712af4655904039ea87affc0c EN eng MDPI AG https://www.mdpi.com/2072-4292/14/2/312 https://doaj.org/toc/2072-4292 doi:10.3390/rs14020312 2072-4292 https://doaj.org/article/a5dd320712af4655904039ea87affc0c Remote Sensing, Vol 14, Iss 312, p 312 (2022) feed-forward neural network the European Arctic Sector partial pressure of CO 2 Air-Sea CO 2 flux Science Q article 2022 ftdoajarticles https://doi.org/10.3390/rs14020312 2022-12-31T07:32:10Z A feed-forward neural network (FFNN) was used to estimate the monthly climatology of partial pressure of CO 2 ( p CO 2W ) at a spatial resolution of 1° latitude by 1° longitude in the continental shelf of the European Arctic Sector (EAS) of the Arctic Ocean (the Greenland, Norwegian, and Barents seas). The predictors of the network were sea surface temperature (SST), sea surface salinity (SSS), the upper ocean mixed-layer depth (MLD), and chlorophyll-a concentration (Chl-a), and as a target, we used 2 853 p CO 2W data points from the Surface Ocean CO 2 Atlas. We built an FFNN based on three major datasets that differed in the Chl-a concentration data used to choose the best model to reproduce the spatial distribution and temporal variability of p CO 2W . Using all physical–biological components improved estimates of the p CO 2W and decreased the biases, even though Chl-a values in many grid cells were interpolated values. General features of p CO 2W distribution were reproduced with very good accuracy, but the network underestimated p CO 2W in the winter and overestimated p CO 2W values in the summer. The results show that the model that contains interpolating Chl-a concentration, SST, SSS, and MLD as a target to predict the spatiotemporal distribution of p CO 2W in the sea surface gives the best results and best-fitting network to the observational data. The calculation of monthly drivers of the estimated p CO 2W change within continental shelf areas of the EAS confirms the major impact of not only the biological effects to the p CO 2W distribution and Air-Sea CO 2 flux in the EAS, but also the strong impact of the upper ocean mixing. A strong seasonal correlation between predictor and p CO 2W seen earlier in the North Atlantic is clearly a yearly correlation in the EAS. The five-year monthly mean CO 2 flux distribution shows that all continental shelf areas of the Arctic Ocean were net CO 2 sinks. Strong monthly CO 2 influx to the Arctic Ocean through the Greenland and Barents Seas (>12 gC m −2 day −1 ) ... Article in Journal/Newspaper Arctic Arctic Ocean Greenland North Atlantic Directory of Open Access Journals: DOAJ Articles Arctic Arctic Ocean Greenland Remote Sensing 14 2 312 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
feed-forward neural network the European Arctic Sector partial pressure of CO 2 Air-Sea CO 2 flux Science Q |
spellingShingle |
feed-forward neural network the European Arctic Sector partial pressure of CO 2 Air-Sea CO 2 flux Science Q Iwona Wrobel-Niedzwiecka Małgorzata Kitowska Przemyslaw Makuch Piotr Markuszewski The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
topic_facet |
feed-forward neural network the European Arctic Sector partial pressure of CO 2 Air-Sea CO 2 flux Science Q |
description |
A feed-forward neural network (FFNN) was used to estimate the monthly climatology of partial pressure of CO 2 ( p CO 2W ) at a spatial resolution of 1° latitude by 1° longitude in the continental shelf of the European Arctic Sector (EAS) of the Arctic Ocean (the Greenland, Norwegian, and Barents seas). The predictors of the network were sea surface temperature (SST), sea surface salinity (SSS), the upper ocean mixed-layer depth (MLD), and chlorophyll-a concentration (Chl-a), and as a target, we used 2 853 p CO 2W data points from the Surface Ocean CO 2 Atlas. We built an FFNN based on three major datasets that differed in the Chl-a concentration data used to choose the best model to reproduce the spatial distribution and temporal variability of p CO 2W . Using all physical–biological components improved estimates of the p CO 2W and decreased the biases, even though Chl-a values in many grid cells were interpolated values. General features of p CO 2W distribution were reproduced with very good accuracy, but the network underestimated p CO 2W in the winter and overestimated p CO 2W values in the summer. The results show that the model that contains interpolating Chl-a concentration, SST, SSS, and MLD as a target to predict the spatiotemporal distribution of p CO 2W in the sea surface gives the best results and best-fitting network to the observational data. The calculation of monthly drivers of the estimated p CO 2W change within continental shelf areas of the EAS confirms the major impact of not only the biological effects to the p CO 2W distribution and Air-Sea CO 2 flux in the EAS, but also the strong impact of the upper ocean mixing. A strong seasonal correlation between predictor and p CO 2W seen earlier in the North Atlantic is clearly a yearly correlation in the EAS. The five-year monthly mean CO 2 flux distribution shows that all continental shelf areas of the Arctic Ocean were net CO 2 sinks. Strong monthly CO 2 influx to the Arctic Ocean through the Greenland and Barents Seas (>12 gC m −2 day −1 ) ... |
format |
Article in Journal/Newspaper |
author |
Iwona Wrobel-Niedzwiecka Małgorzata Kitowska Przemyslaw Makuch Piotr Markuszewski |
author_facet |
Iwona Wrobel-Niedzwiecka Małgorzata Kitowska Przemyslaw Makuch Piotr Markuszewski |
author_sort |
Iwona Wrobel-Niedzwiecka |
title |
The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
title_short |
The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
title_full |
The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
title_fullStr |
The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
title_full_unstemmed |
The Distribution of p CO 2W and Air-Sea CO 2 Fluxes Using FFNN at the Continental Shelf Areas of the Arctic Ocean |
title_sort |
distribution of p co 2w and air-sea co 2 fluxes using ffnn at the continental shelf areas of the arctic ocean |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14020312 https://doaj.org/article/a5dd320712af4655904039ea87affc0c |
geographic |
Arctic Arctic Ocean Greenland |
geographic_facet |
Arctic Arctic Ocean Greenland |
genre |
Arctic Arctic Ocean Greenland North Atlantic |
genre_facet |
Arctic Arctic Ocean Greenland North Atlantic |
op_source |
Remote Sensing, Vol 14, Iss 312, p 312 (2022) |
op_relation |
https://www.mdpi.com/2072-4292/14/2/312 https://doaj.org/toc/2072-4292 doi:10.3390/rs14020312 2072-4292 https://doaj.org/article/a5dd320712af4655904039ea87affc0c |
op_doi |
https://doi.org/10.3390/rs14020312 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
2 |
container_start_page |
312 |
_version_ |
1766320996853219328 |