How accurate are salinity measurements around Antarctica? A machine learning based approach

The Antarctic margin is a critically under-observed region despite its importance to the global climate. Here, in-situ ocean observations are difficult to obtain and clustered in easier-to-access regions. In addition, autonomous salinity measurements have to be corrected for drift or bias after collection. In this work, we introduce a new method that uses neural networks to identify and correct errors in ocean salinity observations. Salinity estimates from a neural network trained on ship-based data are evaluated against Argo and seal measurements around Antarctica. We find that Argo salinity observational errors lie within the bounds of the method uncertainty, validating existing quality control processes for Argo. However, salinity data from seal-mounted sensors have a salty bias below 250m, and is around 0.13±0.06 g/kg 5 months since sensor deployment. Our results showcase a new, flexible and computationally efficient way to assess in-situ ocean data, with potential for global implementation.