Articles | Volume 19, issue 3
https://doi.org/10.5194/bg-19-845-2022
https://doi.org/10.5194/bg-19-845-2022
Research article
 | 
10 Feb 2022
Research article |  | 10 Feb 2022

Reconstruction of global surface ocean pCO2 using region-specific predictors based on a stepwise FFNN regression algorithm

Guorong Zhong, Xuegang Li, Jinming Song, Baoxiao Qu, Fan Wang, Yanjun Wang, Bin Zhang, Xiaoxia Sun, Wuchang Zhang, Zhenyan Wang, Jun Ma, Huamao Yuan, and Liqin Duan

Related authors

A global monthly 3D field of seawater pH over 3 decades: a machine learning approach
Guorong Zhong, Xuegang Li, Jinming Song, Baoxiao Qu, Fan Wang, Yanjun Wang, Bin Zhang, Lijing Cheng, Jun Ma, Huamao Yuan, Liqin Duan, Ning Li, Qidong Wang, Jianwei Xing, and Jiajia Dai
Earth Syst. Sci. Data, 17, 719–740, https://doi.org/10.5194/essd-17-719-2025,https://doi.org/10.5194/essd-17-719-2025, 2025
Short summary

Related subject area

Biogeochemistry: Open Ocean
Composite model-based estimate of the ocean carbon sink from 1959 to 2022
Jens Terhaar
Biogeosciences, 22, 1631–1649, https://doi.org/10.5194/bg-22-1631-2025,https://doi.org/10.5194/bg-22-1631-2025, 2025
Short summary
Phytoplankton community structure in relation to iron and macronutrient fluxes from subsurface waters in the western North Pacific during summer
Huailin Deng, Koji Suzuki, Ichiro Yasuda, Hiroshi Ogawa, and Jun Nishioka
Biogeosciences, 22, 1495–1508, https://doi.org/10.5194/bg-22-1495-2025,https://doi.org/10.5194/bg-22-1495-2025, 2025
Short summary
Intense and localized export of selected marine snow types at eddy edges in the South Atlantic Ocean
Alexandre Accardo, Rémi Laxenaire, Alberto Baudena, Sabrina Speich, Rainer Kiko, and Lars Stemmann
Biogeosciences, 22, 1183–1201, https://doi.org/10.5194/bg-22-1183-2025,https://doi.org/10.5194/bg-22-1183-2025, 2025
Short summary
Spatial distributions of iron and manganese in surface waters of the Arctic's Laptev and East Siberian seas
Naoya Kanna, Kazutaka Tateyama, Takuji Waseda, Anna Timofeeva, Maria Papadimitraki, Laura Whitmore, Hajime Obata, Daiki Nomura, Hiroshi Ogawa, Youhei Yamashita, and Igor Polyakov
Biogeosciences, 22, 1057–1076, https://doi.org/10.5194/bg-22-1057-2025,https://doi.org/10.5194/bg-22-1057-2025, 2025
Short summary
Climate-driven shifts in Southern Ocean primary producers and biogeochemistry in CMIP6 models
Ben J. Fisher, Alex J. Poulton, Michael P. Meredith, Kimberlee Baldry, Oscar Schofield, and Sian F. Henley
Biogeosciences, 22, 975–994, https://doi.org/10.5194/bg-22-975-2025,https://doi.org/10.5194/bg-22-975-2025, 2025
Short summary

Cited articles

Bates, N. R.: Interannual variability of the oceanic CO2 sink in the subtropical gyre of the North Atlantic Ocean over the last 2 decades, J. Geophys. Res.-Oceans, 112, C09013, https://doi.org/10.1029/2006JC003759, 2007. 
Boyer, T. P., Garcia, H. E., Locarnini, R. A., Zweng, M. M., Mishonov, A. V., Reagan, J. R., Weathers, K. A., Baranova, O. K., Seidov, D., and Smolyar, I. V.: World Ocean Atlas 2018 [Dissolved Inorganic Nutrients and Dissolved Oxygen], NOAA National Centers for Environmental Information [data set], https://accession.nodc.noaa.gov/NCEI-WOA18 (last access: 4 August 2020), 2018. 
Broullón, D., Pérez, F. F., Velo, A., Hoppema, M., Olsen, A., Takahashi, T., Key, R. M., Tanhua, T., González-Dávila, M., Jeansson, E., Kozyr, A., and van Heuven, S. M. A. C.: A global monthly climatology of total alkalinity: a neural network approach, Earth Syst. Sci. Data, 11, 1109–1127, https://doi.org/10.5194/essd-11-1109-2019, 2019. 
Broullón, D., Pérez, F. F., Velo, A., Hoppema, M., Olsen, A., Takahashi, T., Key, R. M., Tanhua, T., Santana-Casiano, J. M., and Kozyr, A.: A global monthly climatology of oceanic total dissolved inorganic carbon: a neural network approach, Earth Syst. Sci. Data, 12, 1725–1743, https://doi.org/10.5194/essd-12-1725-2020, 2020. 
Download
Short summary
A predictor selection algorithm was constructed to decrease the predicting error in the surface ocean partial pressure of CO2 (pCO2) mapping by finding better combinations of pCO2 predictors in different regions. Compared with previous research using the same combination of predictors in all regions, using different predictors selected by the algorithm in different regions can effectively decrease pCO2 predicting errors.
Share
Altmetrics
Final-revised paper
Preprint