Analysis of accuracy and efficiency of neural networks to simulate Navier-Stokes fluid flows with obstacles
This work addresses the need for faster and more efficient fluid simulations in obstacle-heavy environments, such as for modeling forest fires or pipe flows, but it is incremental as it applies an existing neural network method to a specific domain.
The paper tackled the problem of time-consuming and energy-intensive fluid simulations by using a neural network to simulate incompressible Navier-Stokes flows with obstacles, achieving low errors (e.g., 0.36% on testing data) and a speedup of approximately 8,800 times compared to conventional methods.
Conventional fluid simulations can be time consuming and energy intensive. We researched the viability of a neural network for simulating incompressible fluids in a randomized obstacle-heavy environment, as an alternative to the numerical simulation of the Navier-Stokes equation. We hypothesized that the neural network predictions would have a relatively low error for simulations over a small number of time steps, but errors would eventually accumulate to the point that the output would become very noisy. Over a rich set of obstacle configurations, we achieved a root mean square error of 0.32% on our training dataset and 0.36% on a testing dataset. These errors only grew to 1.45% and 2.34% at t = 10 and, 2.11% and 4.16% at timestep t = 20. We also found that our selected neural network was approximately 8,800 times faster at predicting the flow than a conventional simulation. Our findings indicate neural networks can be extremely useful at simulating fluids in obstacle-heavy environments. Useful applications include modeling forest fire smoke, pipe fluid flow, and underwater/flood currents.