High-resolution temperature and salinity model analysis using support vector regression
- 136 Downloads
Temperature and salinity in marine data has been studied widely to enhance the marine environmental trend analysis. This work reports a new methodology for deriving high resolution monthly averages of temperature and salinity fields for the Berkeley Canyon based on the use of a support vector regression model. The data used in this paper is from WOA13, BOA Argo and ONC observations. The experimental results show that RBF Kernel function is satisfied with huge, complex marine data. The model is of great robust and adaptability. High resolution climatological means are critical for discerning oceanic features that are of great importance not just to climate systems but also to nutrient cycling and biological habitat. The method will be satisfied with other marine area.
KeywordsTemperature Salinity Support vector regression Underwater sensor network High resolution
This work was supported in part by the National Natural Science Foundation of China (51679105, 61672261, 51409117), Jilin Province Department of Education Thirteen Five science and technology research projects  No. 432,  No. JJKH20170804KJ.
- Kocakulak M, Butun I (2017) An overview of wireless sensor networks towards internet of things. In: 2017 IEEE 7th annual: computing and communication workshop and conference (CCWC), pp. 1–6Google Scholar
- Levitus S, Antonov JI, Baranova OK, Boyer TP, Coleman CL, Garcia HE et al (2013) The world ocean database. Data Sci J 12:WDS229–WDS234Google Scholar
- Wang Y, Cai S, Yin M (2016) Two efficient local search algorithms for maximum weight clique problem. In: AAAI 2016, pp 805–811Google Scholar