Super-Resolution Generative Adversarial Network for Data Compression of Direct Numerical Simulations

Guardat en:
Dades bibliogràfiques
Publicat a:arXiv.org (Dec 18, 2024), p. n/a
Autor principal: Nista, Ludovico
Altres autors: Schumann, Christoph D K, Fröde, Fabian, Gowely, Mohamed, Grenga, Temistocle, MacArt, Jonathan F, Attili, Antonio, Pitsch, Heinz
Publicat:
Cornell University Library, arXiv.org
Matèries:
Accés en línia:Citation/Abstract
Full text outside of ProQuest
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3147267066
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3147267066 
045 0 |b d20241218 
100 1 |a Nista, Ludovico 
245 1 |a Super-Resolution Generative Adversarial Network for Data Compression of Direct Numerical Simulations 
260 |b Cornell University Library, arXiv.org  |c Dec 18, 2024 
513 |a Working Paper 
520 3 |a The advancement of high-performance computing has enabled the generation of large direct numerical simulation (DNS) datasets of turbulent flows, driving the need for efficient compression/decompression techniques that reduce storage demands while maintaining fidelity. Traditional methods, such as the discrete wavelet transform, cannot achieve compression ratios of 8 or higher for complex turbulent flows without introducing significant encoding/decoding errors. On the other hand, super-resolution generative adversarial networks (SR-GANs) can accurately reconstruct fine-scale features, preserving velocity gradients and structural details, even at a compression ratio of 512, thanks to the adversarial training enabled by the discriminator. Their high training time is significantly reduced with a progressive transfer learning approach and, once trained, they can be applied independently of the Reynolds number. It is demonstrated that SR-GANs can enhance dataset temporal resolution without additional simulation overhead by generating high-quality intermediate fields from compressed snapshots. The SR-GAN discriminator can reliably evaluate the quality of decoded fields, ensuring fidelity even in the absence of original DNS fields. Hence, SR-GAN-based compression/decompression methods present a highly efficient and scalable alternative for large-scale DNS storage and transfer, offering substantial advantages in terms of compression efficiency, reconstruction fidelity, and temporal resolution enhancement. 
653 |a Datasets 
653 |a Temporal resolution 
653 |a Wavelet transforms 
653 |a Velocity gradient 
653 |a Data compression 
653 |a Discriminators 
653 |a Discrete Wavelet Transform 
653 |a Generative adversarial networks 
653 |a Fluid flow 
653 |a Domain names 
653 |a Encoding-Decoding 
653 |a Direct numerical simulation 
653 |a Reynolds number 
653 |a Fluid dynamics 
653 |a Compression ratio 
700 1 |a Schumann, Christoph D K 
700 1 |a Fröde, Fabian 
700 1 |a Gowely, Mohamed 
700 1 |a Grenga, Temistocle 
700 1 |a MacArt, Jonathan F 
700 1 |a Attili, Antonio 
700 1 |a Pitsch, Heinz 
773 0 |t arXiv.org  |g (Dec 18, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3147267066/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.14150