Machine Learning Techniques for Data Reduction of CFD Applications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910427074527232 |
|---|---|
| author | Lee, Jaemoon Jung, Ki Sung Gong, Qian Li, Xiao Klasky, Scott Chen, Jacqueline Rangarajan, Anand Ranka, Sanjay |
| author_facet | Lee, Jaemoon Jung, Ki Sung Gong, Qian Li, Xiao Klasky, Scott Chen, Jacqueline Rangarajan, Anand Ranka, Sanjay |
| contents | We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications. It uses a multidimensional block of tensors (spanning in space and time) for both input and output, capturing the spatiotemporal and interspecies relationship within a tensor. The tensor consists of species that represent different elements in a CFD simulation. To guarantee the error bound of the reconstructed data, principal component analysis (PCA) is applied to the residual between the original and reconstructed data. This yields a basis matrix, which is then used to project the residual of each instance. The resulting coefficients are retained to enable accurate reconstruction. Experimental results demonstrate that our approach can deliver two orders of magnitude in reduction while still keeping the errors of primary data under scientifically acceptable bounds. Compared to reduction-based approaches based on SZ, our method achieves a substantially higher compression ratio for a given error bound or a better error for a given compression ratio. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18063 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Machine Learning Techniques for Data Reduction of CFD Applications Lee, Jaemoon Jung, Ki Sung Gong, Qian Li, Xiao Klasky, Scott Chen, Jacqueline Rangarajan, Anand Ranka, Sanjay Machine Learning Fluid Dynamics We present an approach called guaranteed block autoencoder that leverages Tensor Correlations (GBATC) for reducing the spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications. It uses a multidimensional block of tensors (spanning in space and time) for both input and output, capturing the spatiotemporal and interspecies relationship within a tensor. The tensor consists of species that represent different elements in a CFD simulation. To guarantee the error bound of the reconstructed data, principal component analysis (PCA) is applied to the residual between the original and reconstructed data. This yields a basis matrix, which is then used to project the residual of each instance. The resulting coefficients are retained to enable accurate reconstruction. Experimental results demonstrate that our approach can deliver two orders of magnitude in reduction while still keeping the errors of primary data under scientifically acceptable bounds. Compared to reduction-based approaches based on SZ, our method achieves a substantially higher compression ratio for a given error bound or a better error for a given compression ratio. |
| title | Machine Learning Techniques for Data Reduction of CFD Applications |
| topic | Machine Learning Fluid Dynamics |
| url | https://arxiv.org/abs/2404.18063 |