Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition
In this paper, we present a physics-based deep learning framework for data-driven prediction of wave propagation in fluid media. The proposed approach, termed Multistep Integration-Inspired Attention (MI2A), combines a denoising-based convolutional autoencoder for reduced latent representation with an attention-based recurrent neural network with long-short-term memory cells for time evolution of reduced coordinates. This proposed architecture draws inspiration from classical linear multistep methods to enhance stability and long-horizon accuracy in latent-time integration. Despite the efficiency of hybrid neural architectures in modeling wave dynamics, autoregressive predictions are often prone to accumulating phase and amplitude errors over time. To mitigate this issue within the MI2A framework, we introduce a novel loss decomposition strategy that explicitly separates the training loss function into distinct phase and amplitude components. We assess the performance of MI2A against two baseline reduced-order models trained with standard mean-squared error loss: a sequence-to-sequence recurrent neural network and a variant using Luong-style attention. To demonstrate the effectiveness of the MI2A model, we consider three benchmark wave propagation problems of increasing complexity, namely one-dimensional linear convection, the nonlinear viscous Burgers equation, and the two-dimensional Saint-Venant shallow water system. Our results demonstrate that the MI2A framework significantly improves the accuracy and stability of long-term predictions, accurately preserving wave amplitude and phase characteristics. Compared to the standard long-short term memory and attention-based models, MI2A-based deep learning exhibits superior generalization and temporal accuracy, making it a promising tool for real-time wave modeling.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Short-Term Synaptic Plasticity Stabilizes Goal-Conditioned Dynamics in a PFC-Inspired Reservoir Model for Multistep Goal-Directed Action Planning
The prefrontal cortex (PFC) maintains goal information for action planning, but how recurrent circuits preserve it in an action-usable form over behavioral timescales remains unclear. Here we ask whether short-term synap…
Integrating Physics-Informed Deep Learning and Numerical Methods for Robust Dynamics Discovery and Parameter Estimation
Incorporating a priori physics knowledge into machine learning leads to more robust and interpretable algorithms. In this work, we combine deep learning techniques and classic numerical methods for differential equations…
parameter estimationMultivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
This article explores the concepts of ocean wave multivariate multistep forecasting, reconstruction and feature selection. We introduce recurrent neural network frameworks, integrated with Bayesian hyperparameter optimiz…
feature selectionHyperparameter OptimizationTime integration schemes based on neural networks for solving partial differential equations on coarse grids
The accuracy of solving partial differential equations (PDEs) on coarse grids is greatly affected by the choice of discretization schemes. In this work, we propose to learn time integration schemes based on neural networ…
Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes
We propose the multistep port-Hamiltonian Gaussian process (MS-PHS GP) to learn physically consistent continuous-time dynamics and a posterior over the Hamiltonian from noisy, irregularly-sampled trajectories. By placing…
Gaussian Processes