Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation

10/08/2021
by   Wrik Mallik, et al.
0

Although machine learning (ML) is increasingly employed recently for mechanistic problems, the black-box nature of conventional ML architectures lacks the physical knowledge to infer unforeseen input conditions. This implies both severe overfitting during a dearth of training data and inadequate physical interpretability, which motivates us to propose a new kinematically consistent, physics-based ML model. In particular, we attempt to perform physically interpretable learning of inverse problems in wave propagation without suffering overfitting restrictions. Towards this goal, we employ long short-term memory (LSTM) networks endowed with a physical, hyperparameter-driven regularizer, performing penalty-based enforcement of the characteristic geometries. Since these characteristics are the kinematical invariances of wave propagation phenomena, maintaining their structure provides kinematical consistency to the network. Even with modest training data, the kinematically consistent network can reduce the L_1 and L_∞ error norms of the plain LSTM predictions by about 45 also increase the horizon of the plain LSTM's forecasting by almost two times. To achieve this, an optimal range of the physical hyperparameter, analogous to an artificial bulk modulus, has been established through numerical experiments. The efficacy of the proposed method in alleviating overfitting, and the physical interpretability of the learning mechanism, are also discussed. Such an application of kinematically consistent LSTM networks for wave propagation learning is presented here for the first time.

READ FULL TEXT

page 3

page 7

research
01/17/2022

Learning Wave Propagation with Attention-Based Convolutional Recurrent Autoencoder Net

In this paper, we present an end-to-end attention-based convolutional re...
research
02/08/2020

On a scalable entropic breaching of the overfitting barrier in machine learning

Overfitting and treatment of "small data" are among the most challenging...
research
08/09/2017

Tikhonov Regularization for Long Short-Term Memory Networks

It is a well-known fact that adding noise to the input data often improv...
research
05/05/2022

Development of Interpretable Machine Learning Models to Detect Arrhythmia based on ECG Data

The analysis of electrocardiogram (ECG) signals can be time consuming as...
research
04/28/2022

Machine learning for knowledge acquisition and accelerated inverse-design for non-Hermitian systems

Non-Hermitian systems offer new platforms for unusual physical propertie...
research
08/11/2015

Benchmarking of LSTM Networks

LSTM (Long Short-Term Memory) recurrent neural networks have been highly...
research
01/03/2019

Learning a Generator Model from Terminal Bus Data

In this work we investigate approaches to reconstruct generator models f...

Please sign up or login with your details

Forgot password? Click here to reset