Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data (2305.11913v2)

Published 18 May 2023 in physics.ao-ph, cs.AI, and cs.LG

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (78)
  1. Tides and Waves. Encyclopædia metropolitana, John Joseph Griffin and Company.
  2. Mlr and ann models of significant wave height on the west coast of india. Computers and Geosciences 49, 231–237. doi:10.1016/j.cageo.2012.05.032.
  3. Relational inductive biases, deep learning, and graph networks. arXiv arXiv:1806.01261.
  4. Introduction to Inverse Problems in Imaging. CRC Press.
  5. Reconstruction et prévision déterministe de houle à partir de données mesurées. Ph.D. thesis. Ecole Centrale de Nantes (ECN).
  6. Use of nautical radar as a wave monitoring instrument. Coastal Engineering 37, 331–342. doi:10.1016/S0378-3839(99)00032-0.
  7. Inversion of marine radar images for surface wave analysis. Journal of Atmospheric and Oceanic Technology 21, 1291 – 1300. doi:10.1175/1520-0426(2004)021<1291:IOMRIF>2.0.CO;2.
  8. Similarity of the wind wave spectrum in finite depth water: 1. spectral form. Journal of Geophysical Research 90, 975–986.
  9. Spatial–temporal convolutional gated recurrent unit network for significant wave height estimation from shipborne marine radar data. IEEE Transactions on Geoscience and Remote Sensing 60, 1–11. doi:10.1109/TGRS.2021.3074075.
  10. Ocean surface determination from x-band radar-image sequences. Journal of Geophysical Research: Oceans 109. doi:10.1029/2003JC002130.
  11. Neural networks for wave forecasting. Ocean Engineering 28, 889–898. doi:10.1016/S0029-8018(00)00027-5.
  12. Real-time reconstruction and prediction of ocean wave fields from remote optical measurements. Theses. École centrale de Nantes.
  13. Reconstruction of Ocean Surfaces From Randomly Distributed Measurements Using a Grid-Based Method. International Conference on Offshore Mechanics and Arctic Engineering Volume 6: Ocean Engineering. doi:10.1115/OMAE2021-62409.
  14. Nonlinear Reconstruction and Prediction of Regular Waves. International Conference on Offshore Mechanics and Arctic Engineering Volume 5B: Ocean Engineering; Honoring Symposium for Professor Günther F. Clauss on Hydrodynamics and Ocean Engineering. doi:10.1115/OMAE2022-78988.
  15. Wave prediction using wave rider position measurements and narx network in wave energy conversion. Applied Ocean Research 82, 10–21. doi:10.1016/j.apor.2018.10.016.
  16. A high-order spectral method for the study of nonlinear gravity waves. Journal of Fluid Mechanics 184, 267–288. doi:10.1017/S002211208700288X.
  17. Phase-resolved wave prediction model for long-crest waves based on machine learning. Computer Methods in Applied Mechanics and Engineering 372, 113350. doi:10.1016/j.cma.2020.113350.
  18. Numerical investigations on wave remote sensing from synthetic x-band radar sea clutter images by using deep convolutional neural networks. Remote Sensing 12. doi:10.3390/rs12071117.
  19. 3-d hos simulations of extreme waves in open seas. Natural Hazards and Earth System Sciences 7, 109–122. doi:10.5194/nhess-7-109-2007.
  20. Surrogate convolutional neural network models for steady computational fluid dynamics simulations. Electronic Transactions on Numerical Analysis 56, 235–255.
  21. Deep Learning. MIT Press. http://www.deeplearningbook.org.
  22. Measurements of wind-wave growth and swell decay during the joint north sea wave project (jonswap). Ergänzung zur Deutschen Hydrographischen Zeitschrift, Reihe A (8) 12, 1–95.
  23. Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs/1606.08415. arXiv:1606.08415.
  24. Observations of predictive skill for real-time deterministic sea waves from the wamos ii. OCEANS 2015 - MTS/IEEE Washington , 1–7.
  25. Image-to-image translation with conditional adversarial networks. arXiv arXiv:1611.07004.
  26. A machine learning framework to forecast wave conditions. Coastal Engineering 137, 1–10. doi:10.1016/j.coastaleng.2018.03.004.
  27. Forecasting a water-surface wave train with artificial intelligence- a case study. Ocean Engineering 207, 107380. doi:10.1016/j.oceaneng.2020.107380.
  28. Rogue Waves in the Ocean. 1 ed., Springer Berlin Heidelberg. doi:10.1007/978-3-540-88419-4_5.
  29. Adam: A method for stochastic optimization. doi:10.48550/ARXIV.1412.6980.
  30. On the deterministic prediction of water waves. Fluids 5. doi:10.3390/fluids5010009.
  31. Application of Machine Learning for the Generation of Tailored Wave Sequences. International Conference on Offshore Mechanics and Arctic Engineering Volume 5B: Ocean Engineering; Honoring Symposium for Professor Günther F. Clauss on Hydrodynamics and Ocean Engineering. doi:10.1115/OMAE2022-78601.
  32. Nonlinear real time prediction of ocean surface waves. Ocean Engineering 157, 387–400. doi:10.1016/j.oceaneng.2018.03.048.
  33. Deterministic wave prediction for unidirectional sea-states in real-time using artificial neural network. Ocean Engineering 195, 106722. doi:10.1016/j.oceaneng.2019.106722.
  34. Generalization and network design strategies. Connectionism in perspective 19, 18.
  35. Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31.
  36. Fourier neural operator for parametric partial differential equations. arXiv arXiv:2010.08895.
  37. Fourier neural operator approach to large eddy simulation of three-dimensional turbulence. Theoretical and Applied Mechanics Letters 12.
  38. When image denoising meets high-level vision tasks: A deep learning approach, in: Proceedings of the 27th International Joint Conference on Artificial Intelligence, AAAI Press. p. 842–848.
  39. Deterministic wave prediction model for irregular long-crested waves with recurrent neural network. Journal of Ocean Engineering and Science doi:10.1016/j.joes.2022.08.002.
  40. The influence of characteristic sea state parameters on the accuracy of irregular wave field simulations of different complexity. Fluids 7. doi:10.3390/fluids7070243.
  41. The need for biases in learning generalizations. Citeseer.
  42. Rapid phase-resolved prediction of nonlinear dispersive waves using machine learning. Applied Ocean Research 117, 102920. doi:10.1016/j.apor.2021.102920.
  43. Short term forecasting of the sea surface shape. International shipbuilding progress 45, 383–400.
  44. Phase resolved wave prediction from synthetic radar images, in: International Conference on Offshore Mechanics and Arctic Engineering, American Society of Mechanical Engineers. p. V08AT06A045.
  45. Chapter 7 - in situ and remote methods for resource characterization, in: Neill, S.P., Hashemi, M.R. (Eds.), Fundamentals of Ocean Renewable Energy. Academic Press. E-Business Solutions, pp. 157–191. doi:10.1016/B978-0-12-810448-4.00007-0.
  46. A surrogate model for the prediction of permeabilities and flow through porous media: a machine learning approach based on stochastic Brownian motion. Computational Mechanics 71, 563–581. doi:10.1007/s00466-022-02250-2.
  47. Deep learning techniques for inverse problems in imaging. IEEE Journal on Selected Areas in Information Theory 1, 39–56.
  48. Pytorch: An imperative style, high-performance deep learning library. arXiv arXiv:1912.01703.
  49. Context encoders: Feature learning by inpainting, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA. pp. 2536–2544. doi:10.1109/CVPR.2016.278.
  50. Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators. arXiv preprint arXiv:2202.11214.
  51. Attention-enhanced neural network models for turbulence simulation. Physics of Fluids 34, 025111. doi:10.1063/5.0079302.
  52. A robust quantitative comparison criterion of two signals based on the sobolev norm of their difference. Journal of Engineering Mathematics 101, 115–124.
  53. Model evaluation, model selection, and algorithm selection in machine learning. arXiv arXiv:1811.12808.
  54. Learning the stress-strain fields in digital composites using fourier neural operator. iScience 25, 105452. doi:10.1016/j.isci.2022.105452.
  55. U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Springer International Publishing, pp. 234–241. doi:10.1007/978-3-319-24574-4_28.
  56. Significant wave height estimation using svr algorithms and shadowing information from simulated and real measured x-band radar images of the sea surface. Ocean Engineering 101, 244–253. doi:10.1016/j.oceaneng.2015.04.041.
  57. UpsuperscriptU𝑝\hbox{U}^{p}U start_POSTSUPERSCRIPT italic_p end_POSTSUPERSCRIPT-net: a generic deep learning-based time stepper for parameterized spatio-temporal dynamics. Computational Mechanics doi:10.1007/s00466-023-02295-x.
  58. Land cover maps production with high resolution satellite image time series and convolutional neural networks: Adaptations and limits for operational systems. Remote Sensing 11.
  59. Theories for the interaction of electromagnetic and oceanic waves — a review. Boundary-Layer Meteorology 13, 61–85. doi:10.1007/BF00913863.
  60. Estimate of significant wave height from non-coherent marine radar images by multilayer perceptrons. EURASIP Journal on Applied Signal Processing 2012. doi:10.1186/1687-6180-2012-84.
  61. Multi-resolution convolutional neural networks for inverse problems. Scientific reports 10, 1–11.
  62. Physics-guided deep learning for dynamical systems: A survey. arXiv:2107.01272.
  63. Surface similarity parameter: A new machine learning loss metric for oscillatory spatio-temporal data. Neural Networks 156, 123–134. doi:10.1016/j.neunet.2022.09.023.
  64. Machine learning simulation of one-dimensional deterministic water wave propagation. Ocean Engineering 284, 115222. doi:10.1016/j.oceaneng.2023.115222.
  65. U-fno—an enhanced fourier neural operator-based deep-learning model for multiphase flow. Advances in Water Resources 163, 104180. doi:10.1016/j.advwatres.2022.104180.
  66. A new numerical method for surface hydrodynamics. Journal of Geophysical Research: Oceans 92, 11803–11824. doi:10.1029/JC092iC11p11803.
  67. Reconstruction and future prediction of the sea surface from radar observations. Ocean Engineering 106, 261–270. doi:10.1016/j.oceaneng.2015.07.009.
  68. Integrating scientific knowledge with machine learning for engineering and environmental systems. arXiv:2003.04919.
  69. Fourier neural operator for image classification, in: 2022 17th Iberian Conference on Information Systems and Technologies (CISTI), pp. 1–6. doi:10.23919/CISTI54924.2022.9820128.
  70. Direct simulation and deterministic prediction of large-scale nonlinear ocean wave-field. Phd. thesis. Massachusetts Institute of Technology. Department of Ocean Engineering.
  71. Multi-step-ahead forecasting of wave conditions based on a physics-based machine learning (pbml) model for marine operations. Journal of Marine Science and Engineering 8. doi:10.3390/jmse8120992.
  72. A robust deep learning workflow to predict multiphase flow behavior during geological co2 sequestration injection and post-injection periods. Journal of Hydrology 607, 127542. doi:10.1016/j.jhydrol.2022.127542.
  73. Seismic wave propagation and inversion with neural operators. The Seismic Record 1, 126–134.
  74. A deep learning model for improved wind and consequent wave forecasts. Journal of Physical Oceanography 52, 2531 – 2537. doi:10.1175/JPO-D-21-0280.1.
  75. Learning deep implicit fourier neural operators (ifnos) with applications to heterogeneous material modeling. Computer Methods in Applied Mechanics and Engineering 398, 115296. doi:10.1016/j.cma.2022.115296.
  76. Visualizing and understanding convolutional networks, in: Fleet, D., Pajdla, Tomasand Schiele, B., Tuytelaars, T. (Eds.), Computer Vision – ECCV 2014, Springer International Publishing, Cham. pp. 818–83.
  77. Phase-resolved real-time ocean wave prediction with quantified uncertainty based on variational bayesian machine learning. Applied Energy 324, 119711. doi:10.1016/j.apenergy.2022.119711.
  78. Learning deep cnn denoiser prior for image restoration, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3929–3938.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets