A Preliminary Study on Quality Control of Oceanic Observation Data by Machine Learning Methods

Abstract

Argo float is a small and light-weight drifting buoy to measure oceanic temperature and salinity. More than 3,600 floats are always working for globally-covered ocean monitoring, and the accumulated big ocean observation data helps many studies such as investigation into climate change mechanism. However, the observed temperature and salinity data sometimes involves errors. Since automatic detection and correction of the errors is difficult due to ununiform observation reliability and the necessity of specifying error layers, human experts have performed manual error detection and correction. Toward the realization of high-accuracy automatic error detection method, this paper first applies Self-Organizing Map to the observation data for comprehensively understanding of the error characteristics, and then proposes a method for error detection based on Conditional Random Field. Experimental results showed that the proposed classification method based on CRF successfully detected observation errors with significantly better accuracy than the existing automatic quality control method.