Sea surface height super-resolution using high-resolution sea surface temperature with a subpixel convolutional residual network

The oceans have a very important role in climate regulation due to their massive heat storage capacity. Thus, for the past decades, oceans have been observed by satellites to better understand their dynamics. Satellites retrieve several data with various spatial resolutions. For instance, sea surface height (SSH) is a low-resolution data field where sea surface temperature (SST) can be retrieved in a much higher one. These two physical parameters are linked by a physical link that can be learned by a super-resolution machine-learning algorithm. In this work, we present a subpixel convolutional deep learning model that takes advantage of the higher resolution SST field to guide the downscaling of the SSH one. The data fields that we use are simulated by a physic-based ocean model at a higher sampling rate than the satellites provide. We compared our approach with a convolutional neural network model. Our architecture generalized well with validation performances of 3.94 cm root mean squared error (RMSE) and training performances of 2.65 cm RMSE. Impact Statement The dynamics of the oceans are a key issue to understand the climate system, as they transport heat from equatorial areas to colder ones. Ocean currents are therefore an important variable, and their estimation requires to measure the sea surface height (SSH). This altimetry map is hard to acquire in practice and thus has a low effective resolution compared to other physical data such as the sea surface temperature (SST). In this work, we propose a deep learning algorithm that takes advantage of the high-resolution information of the SST to enhance the resolution of the SSH.