Print Email Facebook Twitter Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data Title Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data Author Ehlers, Svenja (Hamburg University of Technology) Klein, Marco (Hamburg University of Technology; Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR)) Heinlein, A. (TU Delft Numerical Analysis) Wedler, Mathies (Hamburg University of Technology) Desmars, Nicolas (Hamburg University of Technology; Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR)) Hoffmann, Norbert (Hamburg University of Technology; Imperial College London) Stender, Merten (Technical University of Berlin) Date 2023 Abstract Accurate short-term predictions of phase-resolved water wave conditions are crucial for decision-making in ocean engineering. However, the initialization of remote-sensing-based wave prediction models first requires a reconstruction of wave surfaces from sparse measurements like radar. Existing reconstruction methods either rely on computationally intensive optimization procedures or simplistic modelling assumptions that compromise the real-time capability or accuracy of the subsequent prediction process. We therefore address these issues by proposing a novel approach for phase-resolved wave surface reconstruction using neural networks based on the U-Net and Fourier neural operator (FNO) architectures. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids, that is generated by the high-order spectral method for wave simulation and a geometric radar modelling approach. The investigation reveals that both models deliver accurate wave reconstruction results and show good generalization for different sea states when trained with spatio-temporal radar data containing multiple historic radar snapshots in each input. Notably, the FNO demonstrates superior performance in handling the data structure imposed by wave physics due to its global approach to learn the mapping between input and output in Fourier space. Subject Deep operator learningFourier neural operatorNonlinear ocean wavesPhase-resolved surface reconstructionRadar inversionX-band radar images To reference this document use: http://resolver.tudelft.nl/uuid:b0855fa0-5a2e-4a4a-9c92-d40fda0315b4 DOI https://doi.org/10.1016/j.oceaneng.2023.116059 Embargo date 2024-04-17 ISSN 0029-8018 Source Ocean Engineering, 288 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 Svenja Ehlers, Marco Klein, A. Heinlein, Mathies Wedler, Nicolas Desmars, Norbert Hoffmann, Merten Stender Files PDF 1_s2.0_S0029801823024435_main.pdf 2.51 MB Close viewer /islandora/object/uuid:b0855fa0-5a2e-4a4a-9c92-d40fda0315b4/datastream/OBJ/view