English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Satellite-based remote sensing missions have revolutionized our understandingof the Ocean state and dynamics. Among them, spaceborne altimetry providesvaluable measurements of Sea Surface Height (SSH), which is used to estimatesurface geostrophic currents. However, due to the sensor technology employed,important gaps occur in SSH observations. Complete SSH maps are produced by thealtimetry community using linear Optimal Interpolations (OI) such as thewidely-used Data Unification and Altimeter Combination System (DUACS). However,OI is known for producing overly smooth fields and thus misses somemesostructures and eddies. On the other hand, Sea Surface Temperature (SST)products have much higher data coverage and SST is physically linked togeostrophic currents through advection. We design a realistic twin experimentto emulate the satellite observations of SSH and SST to evaluate interpolationmethods. We introduce a deep learning network able to use SST information, anda trainable in two settings: one where we have no access to ground truth duringtraining and one where it is accessible. Our investigation involves acomparative analysis of the aforementioned network when trained using eithersupervised or unsupervised loss functions. We assess the quality of SSHreconstructions and further evaluate the network's performance in terms of eddydetection and physical properties. We find that it is possible, even in anunsupervised setting to use SST to improve reconstruction performance comparedto SST-agnostic interpolations. We compare our reconstructions to DUACS's andreport a decrease of 41\% in terms of root mean squared error.

Unsupervised Learning of Sea Surface Height Interpolation from Multi-variate Simulated Satellite Observations