PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics

Abstract

Despite decades of advancements, the simulation of fluids remains one of the most challenging areas of in scientific computing. Supported by the necessity of gradient information in deep learning, differentiable simulators have emerged as an effective tool for optimization and learning in physics simulations. In this work, we present our fluid simulator PICT, a differentiable pressure-implicit solver coded in PyTorch with Graphics-processing-unit (GPU) support. We first verify the accuracy of both the forward simulation and our derived gradients in various established benchmarks like lid-driven cavities and turbulent channel flows before we show that the gradients provided by our solver can be used to learn complicated turbulence models in 2D and 3D. We apply both supervised and unsupervised training regimes using physical priors to match flow statistics. In particular, we learn a stable sub-grid scale (SGS) model for a 3D turbulent channel flow purely based on reference statistics. The low-resolution corrector trained with our solver runs substantially faster than the highly resolved references, while keeping or even surpassing their accuracy. Finally, we give additional insights into the physical interpretation of different solver gradients, and motivate a physically informed regularization technique. To ensure that the full potential of PICT can be leveraged, it is published as open source: https://github.com/tum-pbs/PICT.

Source code at https://github.com/tum-pbs/PICT

References in corpus (20)

• DGM: A deep learning algorithm for solving partial differential equations
• Turbulence Modeling in the Age of Data
• Super-resolution reconstruction of turbulent flows with machine learning
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Assessment of supervised machine learning methods for fluid flows
• GraphCast: Learning skillful medium-range global weather forecasting
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Synthetic turbulent inflow generator using machine learning
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows
• Machine learning building-block-flow wall model for large-eddy simulation
• Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
• Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates
• Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
• Discretize first, filter next: learning divergence-consistent closure models for large-eddy simulation
• Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics
• Quantifying the checkerboard problem to reduce numerical dissipation
• Two-Point Statistics of Coherent Structure in Turbulent Flow