Simulating Three-dimensional Turbulence with Physics-informed Neural Networks
This addresses the high computational cost of turbulence simulation for scientists and engineers, offering a new paradigm for continuous modeling.
The paper tackled the computationally demanding problem of simulating turbulent fluid flows by using physics-informed neural networks (PINNs) to learn solutions directly from physical equations without traditional grids or training data, demonstrating accurate reproduction of key flow statistics such as energy spectra and Reynolds stresses in both two and three dimensions.
Turbulent fluid flows are among the most computationally demanding problems in science, requiring enormous computational resources that become prohibitive at high flow speeds. Physics-informed neural networks (PINNs) represent a radically different approach that trains neural networks directly from physical equations rather than data, offering the potential for continuous, mesh-free solutions. Here we show that appropriately designed PINNs can successfully simulate fully turbulent flows in both two and three dimensions, directly learning solutions to the fundamental fluid equations without traditional computational grids or training data. Our approach combines several algorithmic innovations including adaptive network architectures, causal training, and advanced optimization methods to overcome the inherent challenges of learning chaotic dynamics. Through rigorous validation on challenging turbulence problems, we demonstrate that PINNs accurately reproduce key flow statistics including energy spectra, kinetic energy, enstrophy, and Reynolds stresses. Our results demonstrate that neural equation solvers can handle complex chaotic systems, opening new possibilities for continuous turbulence modeling that transcends traditional computational limitations.