Abstract
The Southern Ocean comprises 25% of the global ocean surface area, accounts for nearly half of the total carbon sink of the global oceans, and is a place that significantly reduces the impacts of anthropogenic CO<sub>2</sub> emissions. Due to the sparsity of observational data, the changes in Southern Ocean carbon sinks over time remain uncertain. In this study, we integrated correlation analysis and a feedforward neural network to improve the accuracy of carbon flux estimations in the Southern Ocean. Based on observation data from 1998–2018, we reconstructed the <i>Southern Ocean's pCO<sub>2</sub></i> grid data during this period. The root-mean-square error obtained by fitting the observation data was 8.86 μatm, indicating that the results were better than those of the two primary statistically based models in the Surface Ocean <i>p</i>CO<sub>2</sub> mapping intercomparison. The results also showed that the Southern Ocean's capacity to act as a carbon sink has gradually increased since 2000; it reduced during 2010–2013 but increased significantly after that. The Southern Ocean's seasonality is characterized by minimum carbon uptake in winter due to increased upwelling; this is followed by a rapid increase toward maximum uptake in summer, which is mainly biologically driven. There is an apparent double-ring structure in the Southern Ocean, as noted in other studies. This study confirms that the inner ring (50–70°S) is a carbon source area gradually transforming into a carbon sink, while the outer ring (35–50°S) continues to serve as a carbon sink.
Highlights
I N THIS study, the Southern Ocean is defined as the area south of 35°S, and is the only ocean that is not divided by continents [1]
The seasonal mean amplitude of surface pCO2 was 13.02 μatm; our products have a similar seasonal trend compared with a station-observed actual data in the Southern Ocean [32], the pCO2 reaching its maximum in winter, and becoming smaller in summer, and the seasonal changes of pCO2 in the Southern Ocean resulted from the combined effects of biological and physical factors [33]
We propose a deep-learning-based method for reconstructing pCO2 data in the Southern Ocean that is generalizable for reconstructing regional data
Summary
I N THIS study, the Southern Ocean is defined as the area south of 35°S, and is the only ocean that is not divided by continents [1]. The inputs include sea surface temperature (SST), sea surface salinity (SSS), the depth of the mixed layer (MLD), chlorophyll concentration (CHL), and other parameters Their results indicated that the Southern Ocean carbon sink stagnated or even decreased between 1980 and 2000, but gradually recovered its original strength in ∼2002. Using the parameters with relatively high correlation coefficients as the input variables of the FFNN, the correlation matrix between pCO2 data and other observed variables is constructed, and correlation parameters are used to reconstruct the pCO2 data in the blank area of the Southern Ocean This method facilitates data analysis and reconstruction for specific regions and improves the current situation wherein sites with limited observation data have higher RMSE values. We analyzed the seasonal, interannual, and interdecadal variations of pCO2 in the Southern Ocean
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
