An Improved PINN Algorithm for Shallow Water Equations Driven by Deep Learning
Open Access
Abstract
Solving shallow water equations is crucial in science and engineering for understanding and predicting natural phenomena. To address the limitations of Physics-Informed Neural Network (PINN) in solving shallow water equations, we propose an improved PINN algorithm integrated with a deep learning framework. This algorithm introduces a regularization term as a penalty in the loss function, based on the PINN and Long Short-Term Memory (LSTM) models, and incorporates an attention mechanism to solve the original equation across the entire domain. Simulation experiments were conducted on one-dimensional and two-dimensional shallow water equations. The results indicate that, compared to the classical PINN algorithm, the improved algorithm shows significant advantages in handling discontinuities, such as sparse waves, in one-dimensional problems. It accurately captures sparse waves and avoids smoothing effects. In two-dimensional problems, the improved algorithm demonstrates good symmetry and effectively reduces non-physical oscillations. It also shows significant advantages in capturing details and handling complex phenomena, offering higher reliability and accuracy. The improved PINNs algorithm, which combines neural networks with physical mechanisms, can provide robust solutions and effectively avoid some of the shortcomings of classical PINNs methods. It also possesses high resolution and strong generalization capabilities, enabling accurate predictions at any given moment.Keywords
Funding Information
- Key Scientific Research Projects Plan of Henan Higher Education Institutions (24A120009)
This publication has 27 references indexed in Scilit:
- High‐order curvilinear Lagrangian finite element methods for shallow water hydrodynamicsInternational Journal for Numerical Methods in Fluids, 2023
- A novel meta-learning initialization method for physics-informed neural networksNeural Computing and Applications, 2022
- PhyCRNet: Physics-informed convolutional-recurrent network for solving spatiotemporal PDEsComputer Methods in Applied Mechanics and Engineering, 2022
- A stable space-time FE method for the shallow water equationsComputational Geosciences, 2021
- Deep Learning for Hyperbolic Conservation Laws with Non‐convex FluxProceedings in Applied Mathematics and Mechanics, 2021
- Physics-informed multi-LSTM networks for metamodeling of nonlinear structuresComputer Methods in Applied Mechanics and Engineering, 2020
- Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problemsComputer Methods in Applied Mechanics and Engineering, 2020
- Physics-informed neural networks for high-speed flowsComputer Methods in Applied Mechanics and Engineering, 2020
- A survey of regularization strategies for deep modelsArtificial Intelligence Review, 2019
- Well-balanced finite volume schemes of arbitrary order of accuracy for shallow water flowsJournal of Computational Physics, 2006