Estimating Subsurface Thermohaline Structure of the Global Ocean Using Surface Remote Sensing Observations

Retrieving multi-temporal and large-scale thermohaline structure information of the interior of the global ocean based on surface satellite observations is important for understanding the complex and multidimensional dynamic processes within the ocean. This study proposes a new ensemble learning algorithm, extreme gradient boosting (XGBoost), for retrieving subsurface thermohaline anomalies, including the subsurface temperature anomaly (STA) and the subsurface salinity anomaly (SSA), in the upper 2000 m of the global ocean. The model combines surface satellite observations and in situ Argo data for estimation, and uses root-mean-square error (RMSE), normalized root-mean-square error (NRMSE), and R2 as accuracy evaluations. The results show that the proposed XGBoost model can easily retrieve subsurface thermohaline anomalies and outperforms the gradient boosting decision tree (GBDT) model. The XGBoost model had good performance with average R2 values of 0.69 and 0.54, and average NRMSE values of 0.035 and 0.042, for STA and SSA estimations, respectively. The thermohaline anomaly patterns presented obvious seasonal variation signals in the upper layers (the upper 500 m); however, these signals became weaker as the depth increased. The model performance fluctuated, with the best performance in October (autumn) for both STA and SSA, and the lowest accuracy occurred in January (winter) for STA and April (spring) for SSA. The STA estimation error mainly occurred in the El Niño-Southern Oscillation (ENSO) region in the upper ocean and the boundary of the ocean basins in the deeper ocean; meanwhile, the SSA estimation error presented a relatively even distribution. The wind speed anomalies, including the u and v components, contributed more to the XGBoost model for both STA and SSA estimations than the other surface parameters; however, its importance at deeper layers decreased and the contributions of the other parameters increased. This study provides an effective remote sensing technique for subsurface thermohaline estimations and further promotes long-term remote sensing reconstructions of internal ocean parameters.

[1]  Xiao‐Hai Yan,et al.  Inconsistent Subsurface and Deeper Ocean Warming Signals During Recent Global Warming and Hiatus , 2017 .

[2]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[3]  Dahai Zhang,et al.  A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost , 2018, IEEE Access.

[4]  Xiaohua Ding,et al.  An objective algorithm for reconstructing the three-dimensional ocean temperature field based on Argo profiles and SST data , 2017, Ocean Dynamics.

[5]  Sabine Vanhuysse,et al.  Very High Resolution Object-Based Land Use–Land Cover Urban Classification Using Extreme Gradient Boosting , 2018, IEEE Geoscience and Remote Sensing Letters.

[6]  Yang Wang,et al.  Reconstructing the Subsurface Temperature Field by Using Sea Surface Data Through Self-Organizing Map Method , 2018, IEEE Geoscience and Remote Sensing Letters.

[7]  Hengqian Yan,et al.  Salinity Profile Estimation in the Pacific Ocean from Satellite Surface Salinity Observations , 2019, Journal of Atmospheric and Oceanic Technology.

[8]  Christopher Chapman,et al.  Reconstruction of Subsurface Velocities From Satellite Observations Using Iterative Self-Organizing Maps , 2016, IEEE Geoscience and Remote Sensing Letters.

[9]  K. Trenberth,et al.  The global warming hiatus: Slowdown or redistribution? , 2016, Earth's future.

[10]  Fouad Badran,et al.  Retrieving the evolution of vertical profiles of Chlorophyll-a from satellite observations using Hidden Markov Models and Self-Organizing Topological Maps , 2015 .

[11]  R. Morrow,et al.  A new estimate of the global 3D geostrophic ocean circulation based on satellite data and in-situ measurements , 2012 .

[12]  Peter R. Oke,et al.  Ensemble data assimilation for an eddy‐resolving ocean model of the Australian region , 2005 .

[13]  Hua Su,et al.  Retrieving Ocean Subsurface Temperature Using a Satellite‐Based Geographically Weighted Regression Model , 2018, Journal of Geophysical Research: Oceans.

[14]  John Abraham,et al.  A review of global ocean temperature observations: Implications for ocean heat content estimates and climate change , 2013, Reviews of Geophysics.

[15]  K. Tung,et al.  Varying planetary heat sink led to global-warming slowdown and acceleration , 2014, Science.

[16]  Yufei Xia,et al.  A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring , 2017, Expert Syst. Appl..

[17]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[18]  Xiao‐Hai Yan,et al.  Estimation of subsurface temperature anomaly in the Indian Ocean during recent global surface warming hiatus from satellite measurements: A support vector machine approach , 2015 .

[19]  Wenhui Xu,et al.  The strong El Niño of 2015/16 and its dominant impacts on global and China's climate , 2016, Journal of Meteorological Research.

[20]  Elahe Akbari,et al.  A Review of Ocean/Sea Subsurface Water Temperature Studies from Remote Sensing and Non-Remote Sensing Methods , 2017 .

[21]  Johann R. E. Lutjeharms,et al.  An altimetry‐based gravest empirical mode south of Africa: 1. Development and validation , 2010 .

[22]  W. Timothy Liu,et al.  Estimation of Subsurface Temperature Anomaly in the North Atlantic Using a Self-Organizing Map Neural Network , 2012 .

[23]  Shiqiu Peng,et al.  Reconstruction of ocean's interior from observed sea surface information , 2017 .

[24]  Hua Su,et al.  Retrieving Temperature Anomaly in the Global Subsurface and Deeper Ocean From Satellite Observations , 2018 .

[25]  Nathaniel L. Bindoff,et al.  Estimating the Four-Dimensional Structure of the Southern Ocean Using Satellite Altimetry , 2011 .

[26]  M. Balmaseda,et al.  Surface warming hiatus caused by increased heat uptake across multiple ocean basins , 2014 .

[27]  M. M. Ali,et al.  Estimation of ocean subsurface thermal structure from surface parameters: A neural network approach , 2004 .

[28]  Kevin E. Trenberth,et al.  Distinctive climate signals in reanalysis of global ocean heat content , 2013 .

[29]  V. Klemas,et al.  Subsurface and deeper ocean remote sensing from satellites: An overview and new results , 2014 .

[30]  Glenn R. Flierl,et al.  Reconstructing the Ocean's Interior from Surface Data , 2013 .

[31]  Hidekatsu Yamazaki,et al.  A Method to Estimate Three-Dimensional Thermal Structure from Satellite Altimetry Data , 2009 .

[32]  S. Peng,et al.  Retrieving density and velocity fields of the ocean's interior from surface data , 2014 .

[33]  Gilles Larnicol,et al.  Combining Argo and remote-sensing data to estimate the ocean three-dimensional temperature fields—a first approach based on simulated observations , 2004 .

[34]  Hua Su,et al.  Subsurface temperature estimation from remote sensing data using a clustering-neural network method , 2019, Remote Sensing of Environment.

[35]  B. Yin,et al.  Seasonal variability in the thermohaline structure of the Western Pacific Warm Pool , 2015, Acta Oceanologica Sinica.

[36]  X. Tie,et al.  Impact of the 2015 El Nino event on winter air quality in China , 2016, Scientific Reports.

[37]  John Abraham,et al.  How fast are the oceans warming? , 2019, Science.

[38]  J. Willis,et al.  Combining altimetric height with broadscale profile data to estimate steric height, heat storage, subsurface temperature, and sea-surface temperature variability , 2003 .

[39]  P. O'Gorman,et al.  Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events , 2018, Journal of Advances in Modeling Earth Systems.

[40]  P. L. Traon,et al.  High Resolution 3-D temperature and salinity fields derived from in situ and satellite observations , 2012 .