Flow reconstruction by multiresolution optimization of a discrete loss with automatic differentiation

Abstract

We present a potent computational method for the solution of inverse problems in fluid mechanics. We consider inverse problems formulated in terms of a deterministic loss function that can accommodate data and regularization terms. We introduce a multigrid decomposition technique that accelerates the convergence of gradient-based methods for optimization problems with parameters on a grid. We incorporate this multigrid technique to the ODIL (Optimizing a DIscrete Loss) framework. The multiresolution ODIL (mODIL) accelerates by an order of magnitude the original formalism and improves the avoidance of local minima. Moreover, mODIL accommodates the use of automatic differentiation for calculating the gradients of the loss function, thus facilitating the implementation of the framework. We demonstrate the capabilities of mODIL on a variety of inverse and flow reconstruction problems: solution reconstruction for the Burgers equation, inferring conductivity from temperature measurements, and inferring the body shape from wake velocity measurements in three dimensions. We also provide a comparative study with the related, popular Physics-Informed Neural Networks (PINNs) method. We demonstrate that mODIL has three to five orders of magnitude lower computational cost than PINNs in benchmark problems including simple PDEs and lid-driven cavity problems. Our results suggest that mODIL is a very potent, fast and consistent method for solving inverse problems in fluid mechanics.

arXiv comment16 pages, 9 figures

References in corpus (10)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport
• Extreme flow simulations reveal skeletal adaptations of deep-sea sponges
• Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
• INFERNO: Galactic winds in dwarf galaxies with star-by-star simulations including runaway stars
• Computing foaming flows across scales: from breaking waves to microfluidics
• Algorithmic aspects of multigrid methods for optimization in shape spaces
• Fluid dynamic shape optimization using self-adapting nonlinear extension operators with multigrid preconditioners
• A Multigrid Preconditioner for Jacobian-free Newton-Krylov Methods

Cited by in corpus (4)

• Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools
• Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss
• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case
• Contactless Precision Steering of Particles in a Fluid inside a Cube with Rotating Walls