%0 Generic %1 wen2021enhanced %A Wen, Gege %A Li, Zongyi %A Azizzadenesheli, Kamyar %A Anandkumar, Anima %A Benson, Sally M. %D 2021 %K ai4science fno neuralpdes todo:read %T U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow %U http://arxiv.org/abs/2109.03697 %X Numerical simulation of multiphase flow in porous media is essential for many geoscience applications. 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), which has shown excellent performance in single-phase flows. We extend the FNO-based architecture to a highly complex CO2-water multiphase problem with wide ranges of permeability and porosity heterogeneity, anisotropy, reservoir conditions, injection configurations, flow rates, and multiphase flow properties. The U-FNO architecture is more accurate in gas saturation and pressure buildup predictions than the original FNO and a state-of-the-art convolutional neural network (CNN) benchmark. Meanwhile, it has superior data utilization efficiency, requiring only a third of the training data to achieve the equivalent accuracy as CNN. U-FNO provides superior performance in highly heterogeneous geological formations and critically important applications such as gas saturation and pressure buildup "fronts" determination. The trained model can serve as a general-purpose alternative to routine numerical simulations of 2D-radial CO2 injection problems with significant speed-ups than traditional simulators.

@misc{wen2021enhanced, abstract = {Numerical simulation of multiphase flow in porous media is essential for many geoscience applications. 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), which has shown excellent performance in single-phase flows. We extend the FNO-based architecture to a highly complex CO2-water multiphase problem with wide ranges of permeability and porosity heterogeneity, anisotropy, reservoir conditions, injection configurations, flow rates, and multiphase flow properties. The U-FNO architecture is more accurate in gas saturation and pressure buildup predictions than the original FNO and a state-of-the-art convolutional neural network (CNN) benchmark. Meanwhile, it has superior data utilization efficiency, requiring only a third of the training data to achieve the equivalent accuracy as CNN. U-FNO provides superior performance in highly heterogeneous geological formations and critically important applications such as gas saturation and pressure buildup "fronts" determination. The trained model can serve as a general-purpose alternative to routine numerical simulations of 2D-radial CO2 injection problems with significant speed-ups than traditional simulators.}, added-at = {2022-10-12T16:44:08.000+0200}, author = {Wen, Gege and Li, Zongyi and Azizzadenesheli, Kamyar and Anandkumar, Anima and Benson, Sally M.}, biburl = {https://www.bibsonomy.org/bibtex/21a1a158ebd52bc3bb0f0f5bfa05bb128/annakrause}, description = {[2109.03697] U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow}, interhash = {434d925735994ee2b8a36af692aa01bd}, intrahash = {1a1a158ebd52bc3bb0f0f5bfa05bb128}, keywords = {ai4science fno neuralpdes todo:read}, note = {cite arxiv:2109.03697}, timestamp = {2022-10-12T16:44:08.000+0200}, title = {U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow}, url = {http://arxiv.org/abs/2109.03697}, year = 2021 }