• Corpus ID: 211252449

Comparing recurrent and convolutional neural networks for predicting wave propagation

  title={Comparing recurrent and convolutional neural networks for predicting wave propagation},
  author={Stathi Fotiadis and Eduardo Pignatelli and Mario Lino Valencia and Chris D. Cantwell and Amos J. Storkey and Anil Anthony Bharath},
Dynamical systems can be modelled by partial differential equations and numerical computations are used everywhere in science and engineering. In this work, we investigate the performance of recurrent and convolutional deep neural network architectures to predict the surface waves. The system is governed by the Saint-Venant equations. We improve on the long-term prediction over previous methods while keeping the inference time at a fraction of numerical simulations. We also show that… 
Predicting the Propagation of Acoustic Waves using Deep Convolutional Neural Networks
A novel approach for numerically propagating acoustic waves in two-dimensional quiescent media has been developed through a fully convolutional multi-scale neural network, resulting in an improved prediction accuracy when adding the spatial gradient difference error to the traditional mean squared error loss function.
On the reproducibility of fully convolutional neural networks for modeling time–space-evolving physical systems
Abstract Reproducibility of a deep-learning fully convolutional neural network is evaluated by training several times the same network on identical conditions (database, hyperparameters, and
Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics
Padding, improved spatial context, and explicit encoding of physical boundaries are investigated in the context of fully convolutional networks applied to recurrent tasks, revealing a high sensitivity of both accuracy and stability on the boundary implementation in such recurrent tasks.
Simulating Surface Wave Dynamics with Convolutional Networks
It is demonstrated that a modified U-Net architecture is capable of accurately predicting the height distribution of waves on a liquid surface within curved and multi-faceted open and closed geometries, when only simple box and right-angled corner geometry were seen during training.
Towards Fast Simulation of Environmental Fluid Mechanics with Multi-Scale Graph Neural Networks
A novel multi-scale graph neural network model for learning to infer unsteady continuum mechanics in problems encompassing a range of length scales and complex boundary geometries, and interpolates to unseen spatial discretisations of the physical domains, allowing it to adopt efficient discretisation and to dynamically and locally modify them to further improve the accuracy.
Convolutional recurrent autoencoder network for learning underwater ocean acoustics
Underwater ocean acoustics is a complex physical phenomenon involving not only widely varying physical parameters and dynamical scales but also uncertainties in the ocean parameters. Thus, it is
Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks
The proposed MultiScaleGNN model is a novel multi-scale graph neural network model for learning to infer unsteady continuum mechanics that can generalise from uniform advection fields to high-gradient fields on complex domains at test time and infer long-term Navier-Stokes solutions within a range of Reynolds numbers.
Disentangled generative models for robust dynamical system prediction
Results indicate that disentangled VAEs adapt better to domain parameters spaces that were not present in the training data and can improve the long-term and out- of-distribution predictions of state-of-the-art models in video sequences.
POD-Enhanced Deep Learning-Based Reduced Order Models for the Real-Time Simulation of Cardiac Electrophysiology in the Left Atrium
It is shown that performing a prior dimensionality reduction on FOM snapshots through randomized proper orthogonal decomposition (POD) enables to speed up training times and to decrease networks complexity.
Implementing Data-Driven Approach for Modelling Ultrasonic Wave Propagation Using Spatio-Temporal Deep Learning (SDL)
A data-driven spatio-temporal deep learning model, to simulate forward and reflected ultrasonic wave propagation in the 2D geometrical domain, by implementing the convolutional long short-term memory (ConvLSTM) algorithm.


Approximating the Solution of Surface Wave Propagation Using Deep Neural Networks
A neural network capable of predicting the evolution of a specific physical phenomenon: propagation of surface waves enclosed in a tank, which, mathematically, can be described by the Saint-Venant equations is proposed.
Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial
Accelerating Eulerian Fluid Simulation With Convolutional Networks
This work proposes a data-driven approach that leverages the approximation power of deep-learning with the precision of standard solvers to obtain fast and highly realistic simulations of the Navier-Stokes equations.
Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
This two part treatise introduces physics informed neural networks – neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.
Deep Fluids: A Generative Network for Parameterized Fluid Simulations
The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence‐free velocity fields at all times, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re‐sampling, latent space simulations, and compression of fluid simulation data.
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.
Learning A Physical Long-term Predictor
This approach demonstrates for the first time the possibility of making actionable long-term predictions from sensor data without requiring to explicitly model the underlying physical laws.
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
A systematic evaluation of generic convolutional and recurrent architectures for sequence modeling concludes that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutionals should be regarded as a natural starting point for sequence modeled tasks.
FlowNet: Learning Optical Flow with Convolutional Networks
This paper constructs CNNs which are capable of solving the optical flow estimation problem as a supervised learning task, and proposes and compares two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
A Gradient Highway architecture is proposed, which provides alternative shorter routes for gradient flows from outputs back to long-range inputs, enabling PredRNN++ to capture short-term and long-term dependencies adaptively and to ease the vanishing gradient problem.