In this letter a new method based on modified selforganizing maps is presented for the reconstruction of deep ocean current velocities from surface information provided by satellites. This method takes advantage of local correlations in the data-space to improve the accuracy of the reconstructed deep velocities. Unlike previous attempts to reconstruct deep velocities from surface data, our method makes no assumptions regarding the structure of the water column, nor the underlying dynamics of the flow field. Using satellite observations of surface velocity, sea-surface height and sea-surface temperature, as well as observations of the deep current velocity from autonomous Argo floats to train the map, we are able to reconstruct realistic high-resolution velocity fields at a depth of 1000m. Validation reveals extremely promising results, with a speed root mean squared error of ∼2.8cm. −1 , a factor more than a factor of two smaller than competing methods, and direction errors consistently smaller than 30 • . Finally, we discuss the merits and shortcomings of this methodology and its possible future applications.

No abstract

Abstract. Studies of coastal seas in Europe have noted the high variability of the CO 2 system. This high variability, generated by the complex mechanisms driving the CO 2 fluxes, complicates the accurate estimation of these mechanisms. This is particularly pronounced in the Baltic Sea, where the mechanisms driving the fluxes have not been characterized in as much detail as in the open oceans. In addition, the joint availability of in situ measurements of CO 2 and of seasurface satellite data is limited in the area. In this paper, we used the SOMLO (self-organizing multiple linear output; Sasse et al., 2013) methodology, which combines two existing methods (i.e. self-organizing maps and multiple linear regression) to estimate the ocean surface partial pressure of CO 2 (pCO 2 ) in the Baltic Sea from the remotely sensed sea surface temperature, chlorophyll, coloured dissolved organic matter, net primary production, and mixed-layer depth. The outputs of this research have a horizontal resolution of 4 km and cover the 1998-2011 period. These outputs give a monthly map of the Baltic Sea at a very fine spatial resolution. The reconstructed pCO 2 values over the validation data set have a correlation of 0.93 with the in situ measurements and a root mean square error of 36 µatm. Removing any of the satellite parameters degraded this reconstructed CO 2 flux, so we chose to supply any missing data using statistical imputation. The pCO 2 maps produced using this method also provide a confidence level of the reconstruction at each grid point. The results obtained are encouraging given the sparsity of available data, and we expect to be able to produce even more accurate reconstructions in coming years, given the predicted acquisition of new data.