Filtered Partial Differential Equations: a robust surrogate constraint in physics-informed deep learning framework

Abstract

Embedding physical knowledge into neural network (NN) training has been a hot topic. However, when facing the complex real-world, most of the existing methods still strongly rely on the quantity and quality of observation data. Furthermore, the neural networks often struggle to converge when the solution to the real equation is very complex. Inspired by large eddy simulation in computational fluid dynamics, we propose an improved method based on filtering. We analyzed the causes of the difficulties in physics informed machine learning, and proposed a surrogate constraint (filtered PDE, FPDE in short) of the original physical equations to reduce the influence of noisy and sparse observation data. In the noise and sparsity experiment, the proposed FPDE models (which are optimized by FPDE constraints) have better robustness than the conventional PDE models. Experiments demonstrate that the FPDE model can obtain the same quality solution with 100% higher noise and 12% quantity of observation data of the baseline. Besides, two groups of real measurement data are used to show the FPDE improvements in real cases. The final results show that FPDE still gives more physically reasonable solutions when facing the incomplete equation problem and the extremely sparse and high-noise conditions. For combining real-world experiment data into physics-informed training, the proposed FPDE constraint is useful and performs well in two real-world experiments: modeling the blood velocity in vessels and cell migration in scratches.

References in corpus (14)

• Turbulence Modeling in the Age of Data
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Physics-informed deep learning for incompressible laminar flows
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
• Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
• Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
• A Lagrangian Dual-based Theory-guided Deep Neural Network
• Stochastic particle advection velocimetry (SPAV): theory, simulations, and proof-of-concept experiments

Cited by in corpus (1)

• Convergent series of Stokes wave of arbitrary height in deep water via machine learning