Trend prediction of the 3D thermocline’s lateral boundary based on the SVR method

In recent years, with the use of the float-based wireless sensor network in the Argo project, a large amount of ocean data has been obtained. These data can be applied to analyze the oceanic thermocline, and the forecasting trend of the thermocline through the SVR method in machine learning is presented in this paper. Firstly, this paper refines the spatial resolution with the SVR method and determines the lateral boundary of the three-dimensional thermocline through the information entropy method. Combined with BOA Argo data from 2004 to 2015, this paper then predicts the thermocline trend (10°–25° S and 55°–80° E) over the next 4 years. The results show that the trend of the three-dimensional thermocline’s lateral boundary can be effectively predicted with the application of SVR method.

[1]  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 .

[2]  M. Gregg,et al.  Diapycnal mixing in the thermocline: A review , 1987 .

[3]  A. A. Zelenko,et al.  Statistical structure of spatial variability of the ocean thermohaline fields from argo profiling data, 2005–2007 , 2010 .

[4]  Yu Zhang,et al.  Environmental preferences of longlining for yellowfin tuna (Thunnus albacares) in the tropical high seas of the Indian Ocean , 2008 .

[5]  David Itano,et al.  Deep diving behavior observed in yellowfin tuna ( Thunnus albacares ) , 2006 .

[6]  Bin Gu,et al.  Incremental Support Vector Learning for Ordinal Regression , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[7]  S. Josey,et al.  On the accuracy of North Atlantic temperature and heat storage fields from Argo , 2007 .

[8]  Tong Zhang,et al.  A Machine Learning Approach to Argo Data Analysis in a Thermocline , 2017, Sensors.

[9]  Li Yan.  Characteristic analysis and calculation of the ocean thermocline , 2011 .

[10]  Michele Tackx,et al.  FACTORS AFFECTING DISTRIBUTION OF ADULT YELLOWFIN TUNA (THUNNUS ALBACARES) AND ITS REPRODUCTIVE ECOLOGY IN THE INDIAN OCEAN BASED ON JAPANESE TUNA LONGLINE FISHERIES AND SURVEY INFORMATION , 2001 .

[11]  张晶 Zhang Jing,et al.  The relationship between the temporal-spatial distribution of fishing ground of yellowfin tuna(Thunnus albacares) and themocline characteristics in the tropic Indian Ocean , 2012 .

[12]  Shigeki Hosoda,et al.  A monthly mean dataset of global oceanic temperature and salinity derived from Argo float observations , 2008 .

[13]  Peter C. Chu,et al.  Geostrophic Circulation in the Tropical North Pacific Ocean Based on Argo Profiles , 2014 .

[14]  XU Jian-ping,et al.  The application of Argo data to water masses analysis in the Northwest Pacific Ocean , 2007 .

[15]  Philippe Lenca,et al.  Coherent heat patterns revealed by unsupervised classification of Argo temperature profiles in the North Atlantic Ocean , 2017 .

[16]  Zhang Yonggang.  Simulation for Acoustic Channel Influenced by Shallow Water Thermocline , 2012 .

[17]  Janet Sprintall,et al.  Southern Ocean mixed-layer depth from Argo float profiles , 2008 .

[18]  Rahul Barman,et al.  A new approach for deriving temperature and salinity fields in the Indian Ocean using artificial neural networks , 2010 .

[19]  Dean Roemmich,et al.  The 2004-2008 mean and annual cycle of temperature, salinity, and steric height in the global ocean from the Argo Program , 2009 .

[20]  Fabienne Gaillard,et al.  Quality Control of Large Argo Datasets , 2009 .

[21]  Bin Gu,et al.  A Robust Regularization Path Algorithm for $\nu $ -Support Vector Classification , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Robert C. Wolpert,et al.  A Review of the , 1985 .

[23]  Xiaofen Wu,et al.  Annual and interannual variations of the Western Pacific Warm Pool volume and sources of warm water revealed by Argo data , 2014, Science China Earth Sciences.

[24]  M. Ravichandran,et al.  An operational Objective Analysis system at INCOIS for generation of Argo Value Added Products , 2007 .

[25]  Lijing Cheng,et al.  Uncertainties of the Ocean Heat Content Estimation Induced by Insufficient Vertical Resolution of Historical Ocean Subsurface Observations , 2014 .