KaRIn Noise Reduction Using a Convolutional Neural Network for the SWOT Ocean Products

• Published in: Remote Sensing
• Main Authors: Tréboutte, Anaëlle, Carli, Elisa, Ballarotta, Maxime, Carpentier, Benjamin, Faugère, Yannice, Dibarboure, Gérald
• Other Authors: Laboratoire d'études en Géophysique et océanographie spatiales (LEGOS), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS)
• Format: Article in Journal/Newspaper
• Language: English
• Published: HAL CCSD 2023
• Subjects: [SPI]Engineering Sciences [physics]; Gomez; Navarro; North Atlantic
• Online Access: https://hal.science/hal-04501384; https://hal.science/hal-04501384/document; https://hal.science/hal-04501384/file/remotesensing-15-02183.pdf; https://doi.org/10.3390/rs15082183

International audience The SWOT (Surface Water Ocean Topography) mission will provide high-resolution and two-dimensional measurements of sea surface height (SSH). However, despite its unprecedented precision, SWOT’s Ka-band Radar Interferometer (KaRIn) still exhibits a substantial amount of random noise. In turn, the random noise limits the ability of SWOT to capture the smallest scales of the ocean’s topography and its derivatives. In that context, this paper explores the feasibility, strengths and limits of a noise-reduction algorithm based on a convolutional neural network. The model is based on a U-Net architecture and is trained and tested with simulated data from the North Atlantic. Our results are compared to classical smoothing methods: a median filter, a Lanczos kernel smoother and the SWOT de-noising algorithm developed by Gomez-Navarro et al. Our U-Net model yields better results for all the evaluation metrics: 2 mm root mean square error, sub-millimetric bias, variance reduction by factor of 44 (16 dB) and an accurate power spectral density down to 10–20 km wavelengths. We also tested various scenarios to infer the robustness and the stability of the U-Net. The U-Net always exhibits good performance and can be further improved with retraining if necessary. This robustness in simulation is very encouraging: our findings show that the U-Net architecture is likely one of the best candidates to reduce the noise of flight data from KaRIn.