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

Abstract

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.

A Transfer Learning-Enhanced Generative Adversarial Network for Downscaling Sea Surface Height through Heterogeneous Data Fusion

“…The PSNR measures the overall image similarity and focuses on assessing the degree of distortion in image colors and smooth areas and is the most widely and commonly used objective metric for evaluating image quality. The formula for PSNR is expressed as follows: PSNR = 10 log 10 255 2 MSE(I HR , I SR ) (11) SSIM can better reflect the subjective perception of human eyes, and the SSIM value is equal to 1 when the content and structure of the two images are identical. SSIM is calculated as follows:…”

“…In recent years, the notable advancements in deep learning within the field of computer vision have led to the emergence of numerous models designed to exploit the dynamic relationships between SSH and SST. These models seek to incorporate SST observations in SSH reconstruction, addressing challenges such as filling missing data [9] or performing data downscaling [10,11]. The former corresponds to a deep learning-based image inpainting problem applied to oceanography, while the latter falls within the domain of the deep learning-based image super-resolution (DLSR) problem.…”

“…RESAC aims to reconstruct high-resolution SSH fields and flow fields with the asistance of high-resolution SST data. Following this, Archambault et al [11] modified the RESAC network and introduced a subpixel convolutional residual network, named RESACsub. Most CNN-based super-resolution methods typically seek to maximize Peak Signal-to-Noise Ratio (PSNR) by minimizing the mean square error (MSE) pixel difference between the reconstructed image and the high-resolution image [12,13,16].…”

Learning Sea Surface Height Interpolation From Multi‐Variate Simulated Satellite Observations

“…Given the losses described in Section 3.3 and a satellite data set (see Section 2.3), we can consider three ways to apply our methodology to the Ocean Data Challenge 2021. We partially presented this experiment in Archambault et al (2024).…”