Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 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

Data repairing and resolution enhancement using data-driven modal decomposition and deep learning (2401.11286v1)

Published 20 Jan 2024 in cs.CE and physics.flu-dyn

Abstract: This paper introduces a new series of methods which combine modal decomposition algorithms, such as singular value decomposition and high-order singular value decomposition, and deep learning architectures to repair, enhance, and increase the quality and precision of numerical and experimental data. A combination of two- and three-dimensional, numerical and experimental dasasets are used to demonstrate the reconstruction capacity of the presented methods, showing that these methods can be used to reconstruct any type of dataset, showing outstanding results when applied to highly complex data, which is noisy. The combination of benefits of these techniques results in a series of data-driven methods which are capable of repairing and/or enhancing the resolution of a dataset by identifying the underlying physics that define the data, which is incomplete or under-resolved, filtering any existing noise. These methods and the Python codes are included in the first release of ModelFLOWs-app.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Shallow neural networks for fluid flow reconstruction with limited sensors, Proceedings of the Royal Society A 476 (2020) 20200097.
  2. Simulating fuel assemblies with low resolution cfd approaches, Nuclear engineering and design 250 (2012) 548–559.
  3. M. Zyskowski, Aircraft simulation techniques used in low-cost, commercial software, in: AIAA Modeling and Simulation Technologies Conference and Exhibit, 2003, p. 5818.
  4. A new automatic, very efficient method for the analysis of flight flutter testing data, Aerospace Science and Technology 114 (2021) 106749.
  5. A predictive physics-aware hybrid reduced order model for reacting flows, arXiv:2301.09860 (2023).
  6. Computational fluid dynamics modelling in cardiovascular medicine, Heart 102 (2016) 18–28.
  7. On the experimental, numerical and data-driven methods to study urban flows, Energies 14 (2021a) 1310.
  8. On the experimental, numerical and data-driven methods to study urban flows, Energies 14(5) (2021b) 1310.
  9. S. Le Clainche, Prediction of the optimal vortex in synthetic jets, Energies 12 (9) (2019).
  10. Repairing occluded data for a mach 0.6 jet via data fusion, AIAA journal 55 (2017) 255–264.
  11. R. Vinuesa, S. L. Brunton, Enhancing computational fluid dynamics with machine learning, Nature Computational Science 2 (2022) 358–366.
  12. Machine learning for fluid mechanics, Annual review of fluid mechanics 52 (2020) 477–508.
  13. C. Downs, S. Jazayeri, Resolution enhancement of deconvolved ground penetrating radar images using singular value decomposition, Journal of Applied Geophysics 193 (2021) 104401.
  14. Two-dimensional tsvd to enhance the spatial resolution of radiometer data, IEEE transactions on geoscience and remote sensing 52 (2013) 2450–2458.
  15. K. Shamna, Satellite image resolution and brightness enhancement using discrete, stationary wavelet and singular value decomposition, in: 2014 International Conference on Power Signals Control and Computations (EPSCICON), IEEE, 2014, pp. 1–4.
  16. S. Intawichai, S. Chaturantabut, A missing data reconstruction method using an accelerated least-squares approximation with randomized svd, Algorithms 15 (2022) 190.
  17. Spatial-temporal traffic speed patterns discovery and incomplete data recovery via svd-combined tensor decomposition, Transportation research part C: emerging technologies 86 (2018) 59–77.
  18. A deep-learning approach for reconstructing 3d turbulent flows from 2d observation data, Scientific Reports 13 (2023) 2529.
  19. Super-resolution gans of randomly-seeded fields, arXiv preprint arXiv:2202.11701 (2022).
  20. T. Bolton, L. Zanna, Applications of deep learning to ocean data inference and subgrid parameterization, Journal of Advances in Modeling Earth Systems 11 (2019) 376–399.
  21. Super-resolution reconstruction of turbulent flows with machine learning, Journal of Fluid Mechanics 870 (2019) 106–120.
  22. Enhancing image resolution and denoising using autoencoder, in: A. Khanna, D. Gupta, Z. Pólkowski, S. Bhattacharyya, O. Castillo (Eds.), Data Analytics and Management, Springer Singapore, Singapore, 2021, pp. 649–659.
  23. Data augmentation using variational autoencoders for improvement of respiratory disease classification, PLOS ONE 17 (2022) 1–41. URL: https://doi.org/10.1371/journal.pone.0266467. doi:10.1371/journal.pone.0266467.
  24. J. Vega, S. Le Clainche, Higher order dynamic mode decomposition and its applications, BOOK: Elsevier (2020).
  25. Higher order dynamic mode decomposition to model reacting flows, International Journal of Mechanical Sciences 249 (2023) 108219. URL: https://www.sciencedirect.com/science/article/pii/S0020740323001212. doi:https://doi.org/10.1016/j.ijmecsci.2023.108219.
  26. On the generation and destruction mechanisms of arch vortices in urban fluid flows, Physics of Fluids 34 (2022) 051702. URL: https://doi.org/10.1063/5.0088305. doi:10.1063/5.0088305.
  27. ModelFLOWs-app: data-driven post-processing and reduced order modelling tools, arXiv preprint arXiv:2305.17150 (2023).
  28. L. Sirovich, Turbulence and the dynamic of coherent structures, parts i–iii, Q. Appl. Math. 45(3) (1987) 561.
  29. J. L. Lumley, The structure of inhomogeneous turbulent flows, In: Yaglam, A.M., Tatarsky, V.I. (eds.) Proceedings of the International Colloquium on the Fine Scale Structure of the Atmosphere and Its Influence on Radio Wave Propagation. Doklady Akademii Nauk SSSR, Nauka, Moscow (1967).
  30. S. Le Clainche, J. M. Vega, Higher order dynamic mode decomposition, SIAM J. Appl. Dyn. Sys. 16 (2) (2017) 882–925.
  31. On the best rank-1111 and rank-(r1,r2,…,rn)subscript𝑟1subscript𝑟2…subscript𝑟𝑛(r_{1},r_{2},\ldots,r_{n})( italic_r start_POSTSUBSCRIPT 1 end_POSTSUBSCRIPT , italic_r start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT , … , italic_r start_POSTSUBSCRIPT italic_n end_POSTSUBSCRIPT ) approximation of higher-order tensors, SIAM J. Matrix. Anal. Appl. (2000a) 1324–1342.
  32. A multilinear singular value decomposition, SIAM J. Matrix. Anal. Appl. (2000b) 1253–1278.
  33. Aerodynamic database reconstruction via gappy high order singular value decomposition, Aerosp. Sci. Tech. 52 (2016) 115–128.
  34. D. Venturi, G. Karniadakis, Gappy data and reconstruction procedures for flow past a cylinder, J. Fluid. Mech. 519 (2004) 315–336.
  35. J. Beckers, M. Rixen, Eof calculations and data filling from incomplete oceanographic datasets, J. Atmos. and Ocean. Tech. 20 (2003) 1839–1856.
  36. The quickhull algorithm for convex hulls, ACM Transactions on Mathematical Software (TOMS) 22 (1996) 469–483.
  37. K. Hormann, Barycentric interpolation, in: Approximation Theory XIV: San Antonio 2013, Springer, 2014, pp. 197–218.
  38. Efficient computation of the pod manifold containing the information required to generate a multi-parameter aerodynamic database, Aerosp. Sci. Tech. 25 (2013) 152–160.
  39. A novel data-driven method for the analysis and reconstruction of cardiac cine mri, Comp. Biolog. Medic. 151 (2022) 106317.
  40. Deep learning combined with singular value decomposition to reconstruct databases in fluid dynamics, Expert Systems with Applications (2024). doi:10.1016/j.eswa.2023.121924.
  41. C. Jackson, A finite-element study of the onset of vortex shedding in flow past variously shaped bodies, Journal of fluid Mechanics 182 (1987) 23–45.
  42. D. Barkley, R. D. Henderson, Three-dimensional floquet stability analysis of the wake of a circular cylinder, Journal of Fluid Mechanics 322 (1996) 215–241.
  43. Spatio-temporal flow structures in the three-dimensional wake of a circular cylinder, Fluid Dyn. Res., in press (2018).
  44. Multiscale proper orthogonal decomposition (mPOD) of TR-PIV data-a case study on stationary and transient cylinder wake flows, Measurement Science and Technology 31 (2020) 094014.
  45. PIV measurements of the wake formation from a rough flat plate, in: 14th International Symposium on Particle Image Velocimetry, volume 1, 2021.
  46. TensorFlow, ???? URL: https://www.tensorflow.org/.

Summary

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