Noise-aware Physics-informed Machine Learning for Robust PDE Discovery

Abstract

This work is concerned with discovering the governing partial differential equation (PDE) of a physical system. Existing methods have demonstrated the PDE identification from finite observations but failed to maintain satisfying results against noisy data, partly owing to suboptimal estimated derivatives and found PDE coefficients. We address the issues by introducing a noise-aware physics-informed machine learning (nPIML) framework to discover the governing PDE from data following arbitrary distributions. We propose training a couple of neural networks, namely solver and preselector, in a multi-task learning paradigm, which yields important scores of basis candidates that constitute the hidden physical constraint. After they are jointly trained, the solver network estimates potential candidates, e.g., partial derivatives, for the sparse regression algorithm to initially unveil the most likely parsimonious PDE, decided according to the information criterion. We also propose the denoising physics-informed neural networks (dPINNs), based on Discrete Fourier Transform (DFT), to deliver a set of the optimal finetuned PDE coefficients respecting the noise-reduced variables. The denoising PINNs are structured into forefront projection networks and a PINN, by which the formerly learned solver initializes. Our extensive experiments on five canonical PDEs affirm that the proposed framework presents a robust and interpretable approach for PDE discovery, applicable to a wide range of systems, possibly complicated by noise.

arXiv comment13 pages, 8 figures, v2, v3: corrected typos and author names, v4, v5: improved notations

References in corpus (22)

• Scikit-learn: Machine Learning in Python
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Physics-informed learning of governing equations from scarce data
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
• Weak SINDy For Partial Differential Equations
• Model selection for dynamical systems via sparse regression and information criteria
• PySINDy: A comprehensive Python package for robust sparse system identification
• Data-driven discovery of PDEs in complex datasets
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• DeepMoD: Deep learning for Model Discovery in noisy data
• Using Noisy or Incomplete Data to Discover Models of Spatiotemporal Dynamics
• DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• Discovery of Nonlinear Dynamical Systems using a Runge-Kutta Inspired Dictionary-based Sparse Regression Approach
• Learning partial differential equations for biological transport models from noisy spatiotemporal data
• Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization
• Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
• abess: A Fast Best Subset Selection Library in Python and R
• Robust discovery of partial differential equations in complex situations

Cited by in corpus (4)

• Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
• Addressing the Non-perturbative Regime of the Quantum Anharmonic Oscillator by Physics-Informed Neural Networks
• Adaptive Uncertainty-Guided Model Selection for Data-Driven PDE Discovery
• Discovery of Quasi-Integrable Equations from traveling-wave data using the Physics-Informed Neural Networks