Timezone: »

 
Poster
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
Filipe de Avila Belbute-Peres · Thomas Economon · Zico Kolter

Wed Jul 15 05:00 AM -- 05:45 AM & Wed Jul 15 04:00 PM -- 04:45 PM (PDT) @ None #None

Solving large complex partial differential equations (PDEs), such as those that arise in computational fluid dynamics (CFD), is a computationally expensive process. This has motivated the use of deep learning approaches to approximate the PDE solutions, yet the simulation results predicted from these approaches typically do not generalize well to truly novel scenarios. In this work, we develop a hybrid (graph) neural network that combines a traditional graph convolutional network with an embedded differentiable fluid dynamics simulator inside the network itself. By combining an actual CFD simulator (run on a much coarser resolution representation of the problem) with the graph network, we show that we can both generalize well to new situations and benefit from the substantial speedup of neural network CFD predictions, while also substantially outperforming the coarse CFD simulation alone.

Author Information

Filipe de Avila Belbute-Peres (Carnegie Mellon University)
Thomas Economon (SU2 Foundation)
Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

More from the Same Authors