Learning Physical Models that Can Respect Conservation Laws

Abstract

Recent work in scientific machine learning (SciML) has focused on incorporating partial differential equation (PDE) information into the learning process. Much of this work has focused on relatively "easy" PDE operators (e.g., elliptic and parabolic), with less emphasis on relatively "hard" PDE operators (e.g., hyperbolic). Within numerical PDEs, the latter problem class requires control of a type of volume element or conservation constraint, which is known to be challenging. Delivering on the promise of SciML requires seamlessly incorporating both types of problems into the learning process. To address this issue, we propose ProbConserv, a framework for incorporating conservation constraints into a generic SciML architecture. To do so, ProbConserv combines the integral form of a conservation law with a Bayesian update. We provide a detailed analysis of ProbConserv on learning with the Generalized Porous Medium Equation (GPME), a widely-applicable parameterized family of PDEs that illustrates the qualitative properties of both easier and harder PDEs. ProbConserv is effective for easy GPME variants, performing well with state-of-the-art competitors; and for harder GPME variants it outperforms other approaches that do not guarantee volume conservation. ProbConserv seamlessly enforces physical conservation constraints, maintains probabilistic uncertainty quantification (UQ), and deals well with shocks and heteroscedasticities. In each case, it achieves superior predictive performance on downstream tasks.

arXiv commentICML 2023, Physica D: Nonlinear Phenomena, Accepted

References in corpus (13)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Fourier Neural Operator for Parametric Partial Differential Equations
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Physics-Informed Neural Operator for Learning Partial Differential Equations
• Multiwavelet-based Operator Learning for Differential Equations
• Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
• Numerical Artifacts in the Generalized Porous Medium Equation: Why Harmonic Averaging Itself Is Not to Blame
• Exact conservation laws for neural network integrators of dynamical systems
• Neural Conservation Laws: A Divergence-Free Perspective
• Learning differentiable solvers for systems with hard constraints
• Numerical Artifacts in the Discontinuous Generalized Porous Medium Equation: How to Avoid Spurious Temporal Oscillations
• Guiding continuous operator learning through Physics-based boundary constraints

Cited by in corpus (4)

• Fourier Neural Operator Surrogate Model to Predict 3D Seismic Waves Propagation
• Physics Informed Neural Networks for Modeling of 3D Flow-Thermal Problems with Sparse Domain Data
• Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems
• Machine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned Fluid-Structure Interaction Simulations