Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools

Abstract

We introduce the Optimizing a Discrete Loss (ODIL) framework for the numerical solution of Partial Differential Equations (PDE) using machine learning tools. The framework formulates numerical methods as a minimization of discrete residuals that are solved using gradient descent and Newton's methods. We demonstrate the value of this approach on equations that may have missing parameters or where no sufficient data is available to form a well-posed initial-value problem. The framework is presented for mesh based discretizations of PDEs and inherits their accuracy, convergence, and conservation properties. It preserves the sparsity of the solutions and is readily applicable to inverse and ill-posed problems. It is applied to PDE-constrained optimization, optical flow, system identification, and data assimilation using gradient descent algorithms including those often deployed in machine learning. We compare ODIL with related approach that represents the solution with neural networks. We compare the two methodologies and demonstrate advantages of ODIL that include significantly higher convergence rates and several orders of magnitude lower computational cost. We evaluate the method on various linear and nonlinear partial differential equations including the Navier-Stokes equations for flow reconstruction problems.

7 pages, 5 figures

References in corpus (4)

• Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
• Limitations of Deep Learning for Inverse Problems on Digital Hardware
• Flow reconstruction by multiresolution optimization of a discrete loss with automatic differentiation
• Data driven gradient flows

Cited by in corpus (8)

• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction
• Nonlinear Discrete-Time Observers with Physics-Informed Neural Networks
• Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss
• Contactless Precision Steering of Particles in a Fluid inside a Cube with Rotating Walls
• Neural inference of fluid-structure interactions from sparse off-body measurements
• Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data
• Computed Tomography (CT)-derived Cardiovascular Flow Estimation Using Physics-Informed Neural Networks Improves with Sinogram-based Training: A Simulation Study