Bridging the gap: machine learning to resolve improperly modeled dynamics

DOI10.1016/J.PHYSD.2020.132736zbMATH Open1486.68160arXiv2008.12642OpenAlexW3081881792MaRDI QIDQ2116291FDOQ2116291

Authors: Maan Qraitem, Dhanushka Kularatne, Eric Forgoston, M. Ani Hsieh 

Publication date: 16 March 2022

Published in: Physica D (Search for Journal in Brave)

Abstract: We present a data-driven modeling strategy to overcome improperly modeled dynamics for systems exhibiting complex spatio-temporal behaviors. We propose a Deep Learning framework to resolve the differences between the true dynamics of the system and the dynamics given by a model of the system that is either inaccurately or inadequately described. Our machine learning strategy leverages data generated from the improper system model and observational data from the actual system to create a neural network to model the dynamics of the actual system. We evaluate the proposed framework using numerical solutions obtained from three increasingly complex dynamical systems. Our results show that our system is capable of learning a data-driven model that provides accurate estimates of the system states both in previously unobserved regions as well as for future states. Our results show the power of state-of-the-art machine learning frameworks in estimating an accurate prior of the system's true dynamics that can be used for prediction up to a finite horizon.

Full work available at URL: https://arxiv.org/abs/2008.12642

Recommendations

• A framework for machine learning of model error in dynamical systems
• The discovery of dynamics via linear multistep methods and deep learning: error estimation
• Time-series machine-learning error models for approximate solutions to parameterized dynamical systems
• Multibody dynamics and control using machine learning
• Physics-informed machine learning for reduced-order modeling of nonlinear problems
• Discrete-time nonlinear feedback linearization via physics-informed machine learning
• Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
• A proposal on machine learning via dynamical systems
• Machine learning for prediction with missing dynamics
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems

zbMATH Keywords

machine learningneural networksnonlinear dynamical systemsdata-driven modelinglong short-term memory (LSTM)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Approximation methods and numerical treatment of dynamical systems (37M99)

Cites Work

• Adaptive subgradient methods for online learning and stochastic optimization
• Title not available (Why is that?)
• Deep learning
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Automated reverse engineering of nonlinear dynamical systems
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• Modeling and nonlinear parameter estimation with Kronecker product representation for coupled oscillators and spatiotemporal systems
• Geometric data analysis. An empirical approach to dimensionality reduction and the study of patterns
• Inferring solutions of differential equations using noisy multi-fidelity data
• Machine learning of linear differential equations using Gaussian processes
• Numerical Gaussian processes for time-dependent and nonlinear partial differential equations
• Deep hidden physics models: deep learning of nonlinear partial differential equations
• A Sparse Bayesian Approach to the Identification of Nonlinear State-Space Systems
• Subgrid modelling for two-dimensional turbulence using neural networks
• A supervised neural network for drag prediction of arbitrary 2D shapes in laminar flows at low Reynolds number
• Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network
• Prediction of aerodynamic flow fields using convolutional neural networks
• How entropic regression beats the outliers problem in nonlinear system identification
• Deep learning models for global coordinate transformations that linearise PDEs
• Data-driven prediction of unsteady flow over a circular cylinder using deep learning

Cited In (3)

• Knowledge-based learning of nonlinear dynamics and chaos
• Conservative deep neural networks for modeling competition of ribosomes with extended length
• Bayesian learning of stochastic dynamical models

Uses Software

• Keras
• ImageNet
• Adam
• AntisymmetricRNN
• AlexNet

This page was built for publication: Bridging the gap: machine learning to resolve improperly modeled dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2116291)