Application of Machine Learning Techniques to Ocean Mooring Time-Series Data

Abstract

In situ observations are vital to improving our understanding of the variability and dynamics of the ocean. A critical component of the ocean circulation are the strong, narrow and highly variable western boundary currents. Ocean moorings that extend from the sea floor to the surface remain the most effective and efficient method to fully observe these currents. For various reasons mooring instruments may not provide continuous records. Here we assess the application of the Iterative Completion Self Organising Maps (ITCOMPSOM) machine learning technique to fill observational data gaps in a 7.5 year time-series of the East Australian Current. The method was validated by withholding parts of fully known profiles, and reconstructing them. For 20% random withholding of known velocity data validation statistics of the u- and v-velocity components are R2 coefficients of 0.70 and 0.88 and, root mean square errors of 0.038 m s−1 and 0.064 m s−1, respectively. Withholding 100 days of known velocity profiles over a depth range between 60 m to 700 m has mean profile residual differences between true and predicted u- and v-velocity of 0.009 m s−1 and 0.02 m s−1, respectively. The ITCOMPSOM also reproduces the known velocity variability. For 20% withholding of temperature and salinity data root mean square error of 0.04 and 0.38°C, respectively, are obtained. The ITCOMPSOM validation statistics are significantly better than those obtained when standard data filling methods are used. We suggest that machine learning techniques can be an appropriate method to fill missing data and enable production of observational-derived data products.