Summary of Machine Learning Techniques For Data Reduction Of Cfd Applications, by Jaemoon Lee et al.
Machine Learning Techniques for Data Reduction of CFD Applications
by Jaemoon Lee, Ki Sung Jung, Qian Gong, Xiao Li, Scott Klasky, Jacqueline Chen, Anand Rangarajan, Sanjay Ranka
First submitted to arxiv on: 28 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Fluid Dynamics (physics.flu-dyn)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed guaranteed block autoencoder (GBATC) leverages Tensor Correlations to reduce spatiotemporal data generated by computational fluid dynamics (CFD) and other scientific applications. This approach uses a multidimensional block of tensors, capturing relationships between species in CFD simulations. By applying principal component analysis (PCA) to residuals, GBATC guarantees error bounds on reconstructed data. Experimental results show that GBATC achieves two orders of magnitude reduction while maintaining scientifically acceptable errors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GBATC is a new way to reduce big scientific data. It uses special blocks called tensors to capture relationships between different parts of the data. This helps keep the original information, but makes it much smaller. Scientists can use this method to make their data more manageable and easier to work with. The results are impressive – it reduces the data by a lot while still keeping it accurate. |
Keywords
» Artificial intelligence » Autoencoder » Pca » Principal component analysis » Spatiotemporal
