DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data
read the original abstract
In recent years, data-driven methods have been developed to learn dynamical systems and partial differential equations (PDE). The goal of such work is discovering unknown physics and the corresponding equations. However, prior to achieving this goal, major challenges remain to be resolved, including learning PDE under noisy data and limited discrete data. To overcome these challenges, in this work, a deep-learning based data-driven method, called DL-PDE, is developed to discover the governing PDEs of underlying physical processes. The DL-PDE method combines deep learning via neural networks and data-driven discovery of PDE via sparse regressions. In the DL-PDE, a neural network is first trained, and then a large amount of meta-data is generated, and the required derivatives are calculated by automatic differentiation. Finally, the form of PDE is discovered by sparse regression. The proposed method is tested with physical processes, governed by groundwater flow equation, convection-diffusion equation, Burgers equation and Korteweg-de Vries (KdV) equation, for proof-of-concept and applications in real-world engineering settings. The proposed method achieves satisfactory results when data are noisy and limited.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
EqOD: Symmetry-Informed Stability Selection for PDE Identification
EqOD combines symmetry-based library reduction with stability selection to reach F1=1.000 on several noisy PDE identification tasks where prior methods fail.
-
Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion
PINN achieves 91% accuracy in 3D noisy heat diffusion vs 36% for FDM and 3.3x better error reduction in physical experiment, with efficiency gains in high dimensions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.