Abstract
Meso- and fine-scale sea surface temperature (SST) is an essential parameter in oceanographic research. Remote sensing is an efficient way to acquire global SST. However, single infrared-based and microwave-based satellite-derived SST cannot obtain complete coverage and high-resolution SST simultaneously. Deep learning super-resolution (SR) techniques have exhibited the ability to enhance spatial resolution, offering the potential to reconstruct the details of SST fields. Current SR research focuses mainly on improving the structure of the SR model instead of training dataset selection. Different from generating the low-resolution images by downscaling the corresponding high-resolution images, the high- and low-resolution SST are derived from different sensors. Hence, the structure similarity of training patches may affect the SR model training and, consequently, the SST reconstruction. In this study, we first discuss the influence of training dataset selection on SST SR performance, showing that the training dataset determined by the structure similarity index (SSIM) of 0.6 can result in higher reconstruction accuracy and better image quality. In addition, in the practical stage, the spatial similarity between the low-resolution input and the objective high-resolution output is a key factor for SST SR. Moreover, the training dataset obtained from the actual AMSR2 and MODIS SST images is more suitable for SST SR because of the skin and sub-skin temperature difference. Finally, the SST reconstruction accuracies obtained from different SR models are relatively consistent, yet the differences in reconstructed image quality are rather significant.
Highlights
Meso- and fine-scale sea surface temperature (SST) is a key parameter for the research of the sub-mesoscale oceanic dynamic process, as well as the basic data for mesoscale oceanic front and eddy detection
We calculated the root mean squared error (RMSE), mean absolute error (MAE), and peak signal-to-noise ratio (PSNR) for the four experimental regions using the selected SR models trained based on different training datasets determined by various structure similarity index (SSIM) thresholds
We discuss another SR training strategy, i.e., instead of generating the training dataset based on the advanced microwave scanning radiometer2 (AMSR2) and moderate resolution imaging spectroradiometer (MODIS) SST fields, the training dataset was generated only based on the MODIS SST field, the training dataset was generated only based on the MODIS SST field
Summary
Meso- and fine-scale sea surface temperature (SST) is a key parameter for the research of the sub-mesoscale oceanic dynamic process, as well as the basic data for mesoscale oceanic front and eddy detection. The remote sensing technique is an efficient way to acquire global SST. There are two kinds of satellite-derived SST, including infrared-based SST, such as the moderate resolution imaging spectroradiometer (MODIS). Data, and microwave-based SST, such as the advanced microwave scanning radiometer. As shown, single infrared-based and microwavebased satellite-derived SST cannot obtain complete coverage and high-resolution SST simultaneously. Complete and high-resolution SST reconstruction is an essential topic in oceanographical remote sensing. Multi-source SST fusion methods, such as the optimal interpolation method [1,2,3], and SST spatio-temporal reconstruction methods, such as the data interpolating empirical orthogonal functions (DINEOF) [4,5,6,7,8,9,10,11], are two main
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
