Generative AI for fast and accurate statistical computation of fluids
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910809600294912 |
|---|---|
| author | Molinaro, Roberto Lanthaler, Samuel Raonić, Bogdan Rohner, Tobias Armegioiu, Victor Simonis, Stephan Grund, Dana Ramic, Yannick Wan, Zhong Yi Sha, Fei Mishra, Siddhartha Zepeda-Núñez, Leonardo |
| author_facet | Molinaro, Roberto Lanthaler, Samuel Raonić, Bogdan Rohner, Tobias Armegioiu, Victor Simonis, Stephan Grund, Dana Ramic, Yannick Wan, Zhong Yi Sha, Fei Mishra, Siddhartha Zepeda-Núñez, Leonardo |
| contents | We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on an end-to-end conditional score-based diffusion model. Through extensive numerical experimentation with a set of challenging fluid flows, we demonstrate that GenCFD provides an accurate approximation of relevant statistical quantities of interest while also efficiently generating high-quality realistic samples of turbulent fluid flows and ensuring excellent spectral resolution. In contrast, ensembles of deterministic ML algorithms, trained to minimize mean square errors, regress to the mean flow. We present rigorous theoretical results uncovering the surprising mechanisms through which diffusion models accurately generate fluid flows. These mechanisms are illustrated with solvable toy models that exhibit the mathematically relevant features of turbulent fluid flows while being amenable to explicit analytical formulae. Our codes are publicly available at https://github.com/camlab-ethz/GenCFD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18359 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative AI for fast and accurate statistical computation of fluids Molinaro, Roberto Lanthaler, Samuel Raonić, Bogdan Rohner, Tobias Armegioiu, Victor Simonis, Stephan Grund, Dana Ramic, Yannick Wan, Zhong Yi Sha, Fei Mishra, Siddhartha Zepeda-Núñez, Leonardo Machine Learning Numerical Analysis Fluid Dynamics We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on an end-to-end conditional score-based diffusion model. Through extensive numerical experimentation with a set of challenging fluid flows, we demonstrate that GenCFD provides an accurate approximation of relevant statistical quantities of interest while also efficiently generating high-quality realistic samples of turbulent fluid flows and ensuring excellent spectral resolution. In contrast, ensembles of deterministic ML algorithms, trained to minimize mean square errors, regress to the mean flow. We present rigorous theoretical results uncovering the surprising mechanisms through which diffusion models accurately generate fluid flows. These mechanisms are illustrated with solvable toy models that exhibit the mathematically relevant features of turbulent fluid flows while being amenable to explicit analytical formulae. Our codes are publicly available at https://github.com/camlab-ethz/GenCFD. |
| title | Generative AI for fast and accurate statistical computation of fluids |
| topic | Machine Learning Numerical Analysis Fluid Dynamics |
| url | https://arxiv.org/abs/2409.18359 |