Jiye Zeng , Tsuneo Matsunaga, Nobuko Saigusa, Tomoko Shirai, Shin-ichiro Nakaoka, and Zheng-Hong Tan

Abstract. Reconstructing surface ocean CO₂ from scarce measurements plays an important role in estimating oceanic CO₂ uptake. There are varying degrees of differences among the 14 models included in the Surface Ocean CO₂ Mapping (SOCOM) inter-comparison initiative, in which five models used neural networks. This investigation evaluates two neural networks used in SOCOM, self-organizing maps and feedforward neural networks, and introduces a machine learning model called a support vector machine for ocean CO₂ mapping. The technique note provides a practical guide to selecting the models.

How to cite. Zeng, J., Matsunaga, T., Saigusa, N., Shirai, T., Nakaoka, S., and Tan, Z.-H.: Technical note: Evaluation of three machine learning models for surface ocean CO₂ mapping, Ocean Sci., 13, 303–313, https://doi.org/10.5194/os-13-303-2017, 2017.

Download

• Article (4220 KB)
• Full-text XML

• BibTeX
• EndNote

Short summary

Three machine learning models were investigated for the reconstruction of global surface ocean CO₂ concentration. They include self-organizing maps (SOMs), feedforward neural networks (FNNs), and support vector machines (SVMs). Our results show that the SVM performs the best, the FNN the second, and the SOM the worst. While the SOM does not have over-fitting problems, it is sensitive to data scaling and its discrete interpolation may not be good for some applications.

Three machine learning models were investigated for the reconstruction of global surface ocean...

Read more

Share