Physics Constrained Learning for Data-driven Inverse Modeling from Sparse Observations

Abstract

Deep neural networks (DNN) have been used to model nonlinear relations between physical quantities. Those DNNs are embedded in physical systems described by partial differential equations (PDE) and trained by minimizing a loss function that measures the discrepancy between predictions and observations in some chosen norm. This loss function often includes the PDE constraints as a penalty term when only sparse observations are available. As a result, the PDE is only satisfied approximately by the solution. However, the penalty term typically slows down the convergence of the optimizer for stiff problems. We present a new approach that trains the embedded DNNs while numerically satisfying the PDE constraints. We develop an algorithm that enables differentiating both explicit and implicit numerical solvers in reverse-mode automatic differentiation. This allows the gradients of the DNNs and the PDE solvers to be computed in a unified framework. We demonstrate that our approach enjoys faster convergence and better stability in relatively stiff problems compared to the penalty method. Our approach allows for the potential to solve and accelerate a wide range of data-driven inverse modeling, where the physical constraints are described by PDEs and need to be satisfied accurately.

44 pages, 13 figures

References in corpus (7)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• Isogeometric analysis: an overview and computer implementation aspects
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• A framework for automated PDE-constrained optimisation
• Automatic differentiation in ML: Where we are and where we should be going

Cited by in corpus (13)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• Characterizing possible failure modes in physics-informed neural networks
• Deep Learning for One-dimensional Consolidation
• HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
• ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks
• Inverse Modeling of Viscoelasticity Materials using Physics Constrained Learning
• Physics-informed deep learning for flow and deformation in poroelastic media
• AdjointNet: Constraining machine learning models with physics-based codes
• Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks
• How machine learning can help the design and analysis of composite materials and structures?
• Distributed Machine Learning for Computational Engineering using MPI
• Trust Region Method for Coupled Systems of PDE Solvers and Deep Neural Networks