Super-Resolution Generative Adversarial Network for Data Compression of Direct Numerical Simulations
保存先:
| 出版年: | arXiv.org (Dec 18, 2024), p. n/a |
|---|---|
| 第一著者: | |
| その他の著者: | , , , , , , |
| 出版事項: |
Cornell University Library, arXiv.org
|
| 主題: | |
| オンライン･アクセス: | Citation/Abstract Full text outside of ProQuest |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 抄録: | 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. |
|---|---|
| ISSN: | 2331-8422 |
| ソース: | Engineering Database |