GitHub - gegewen/ufno: U-FNO - an enhanced Fourier neural …
网页U-FNO - an enhanced Fourier neural operator-based deep-learning model for multiphase flow. In this work, we introduce a model architecture, [U-FNO] …
[2109.03697] U-FNO -- An enhanced Fourier neural operator …
网页2021年9月3日 · Here we present U-FNO, a novel neural network architecture for solving multiphase flow problems with superior accuracy, speed, and data efficiency. U-FNO is designed based on the newly proposed Fourier neural operator (FNO), which has shown excellent performance in single-phase flows.
网页Here we present U-FNO, a novel neural network architecture for solving mul-tiphase ow problems with superior accuracy, speed, and data e ciency. U-FNO is designed based on the newly proposed Fourier neural operator (FNO), which has shown excellent performance in single-phase ows.
ufno/README.md at main · gegewen/ufno · GitHub
网页U-FNO - an enhanced Fourier neural operator-based deep-learning model for multiphase flow. In this work, we introduce a model architecture, [U-FNO] …
[2109.03697] U-FNO - an enhanced Fourier neural operator-based …
网页U-FNO - an enhanced Fourier neural operator-based deep-learning model for multiphase flow. Gege Wen Zongyi Li Kamyar Azizzadenesheli Anima Anandkumar Sally M. Benson. Abstract. Numerical simulation of multiphase flow in porous media is essential for many geoscience applications.
U-FNO - an enhanced Fourier neural operator-based deep
网页@article{wen2022u,\n title={U-FNO--An enhanced Fourier neural operator-based deep-learning model for multiphase flow},\n author={Wen, Gege and Li, Zongyi and Azizzadenesheli, Kamyar and Anandkumar, Anima and Benson, Sally M},\n journal={Advances in Water Resources},\n pages={104180},\n year={2022},\n publisher={Elsevier}\n}\n
U-FNO—An enhanced Fourier neural operator-based deep …
网页Machine learning models trained with numerical simulation data can provide a faster alternative to traditional simulators. Here we present U-FNO, a novel neural network architecture for solving multiphase flow problems with superior accuracy, speed, and data efficiency. U-FNO is designed based on the newly proposed Fourier neural operator (FNO ...
U-FNO - Semantic Scholar
网页2021年9月3日 · A Fourier-enhanced multiple-input neural operator (Fourier-MIONet) to learn the solution operator of the problem of multiphase flow in porous media and has 90% fewer unknown parameters, and can be trained in significantly less time to achieve similar prediction accuracy. Expand.
U-FNO—An enhanced Fourier neural operator-based deep …
网页2022年5月1日 · Introduction. Multiphase flow in porous media is important for many geoscience applications, including contaminant transport (Bear and Cheng, 2010), carbon capture and storage (CCS) (Pachauri et al., 2014), hydrogen storage (Hashemi et al., 2021), oil and gas extraction (Aziz, 1979), and nuclear waste storage (Amaziane et al., 2012).
网页U-FNO is designed based on the newly proposed Fourier neural operator (FNO) that learns an in nite di-mensional integral kernel in the Fourier space, which has shown excellent per-formance for single-phase ows.
跳至内容