Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise

DOI10.1137/17M1151900zbMATH Open1391.60083arXiv1710.04586OpenAlexW2962837870MaRDI QIDQ5745136FDOQ5745136

Alexandros Beskos, Francesc Pons Llopis, Nikolas Kantas, Ajay Jasra

Publication date: 5 June 2018

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Abstract: We consider a non-linear filtering problem, whereby the signal obeys the stochastic Navier-Stokes equations and is observed through a linear mapping with additive noise. The setup is relevant to data assimilation for numerical weather prediction and climate modelling, where similar models are used for unknown ocean or wind velocities. We present a particle filtering methodology that uses likelihood informed importance proposals, adaptive tempering, and a small number of appropriate Markov Chain Monte Carlo steps. We provide a detailed design for each of these steps and show in our numerical examples that they are all crucial in terms of achieving good performance and efficiency.

Full work available at URL: https://arxiv.org/abs/1710.04586

Recommendations

• scientific article; zbMATH DE number 849895
• scientific article; zbMATH DE number 2134054
• Nonlinear filtering of stochastic Navier-Stokes equation with Itô-Lévy noise
• Efficient particle filtering for stochastic Korteweg-de Vries equations
• Particle filtering for demodulation in fading channels with non-Gaussian additive noise
• Particle Filters for nonlinear data assimilation in high-dimensional systems
• A particle filter for stochastic advection by Lie transport: a case study for the damped and forced incompressible two-dimensional Euler equation
• Convergence of particle filtering method for nonlinear estimation of vortex dynamics
• scientific article

zbMATH Keywords

particle filtersstochastic filteringstochastic Navier-Stokespreconditioned Crank-Nicolson Markov chain Monte Carlo

Mathematics Subject Classification ID

Filtering in stochastic control theory (93E11) Signal detection and filtering (aspects of stochastic processes) (60G35) Navier-Stokes equations (35Q30)

Cites Work

• Sequential Monte Carlo Methods in Practice
• Sequential Monte Carlo Samplers
• Nonlinear data assimilation
• Nonasymptotic analysis of adaptive and annealed Feynman-Kac particle models
• A stable particle filter for a class of high-dimensional state-space models
• Filtering Complex Turbulent Systems
• A sequential particle filter method for static models
• A note on Metropolis-Hastings kernels for general state spaces
• Inverse problems: a Bayesian perspective
• Stochastic Equations in Infinite Dimensions
• Overcoming the order barrier in the numerical approximation of stochastic partial differential equations with additive space–time noise
• Bayesian inference for nonlinear multivariate diffusion models observed with error
• Mathematics of two-dimensional turbulence.
• Data Assimilation
• Implicit particle filters for data assimilation
• Fundamentals of stochastic filtering
• Mean field simulation for Monte Carlo integration
• Inference for Lévy-driven stochastic volatility models via adaptive sequential Monte Carlo
• On the convergence of adaptive sequential Monte Carlo methods
• Sequential Monte Carlo Methods for High-Dimensional Inverse Problems: A Case Study for the Navier--Stokes Equations
• MCMC methods for functions: modifying old algorithms to make them faster
• Proposals which speed up function-space MCMC
• Large deviation for Navier-Stokes equations with small stochastic perturbation
• Dissipativity and invariant measures for stochastic Navier-Stokes equations
• Dimensional reduction for a Bayesian filter
• Particle filtering with path sampling and an application to a bimodal ocean current model
• Comparison of sequential data assimilation methods for the Kuramoto-Sivashinsky equation
• Determining white noise forcing from Eulerian observations in the Navier-Stokes equation
• Dimension-independent likelihood-informed MCMC
• Stochastic Navier-Stokes equations: Analysis of the noise to have a unique invariant measure
• References
• Data Assimilation
• Bayesian estimation of incompletely observed diffusions
• Title not available (Why is that?)
• Application of Girsanov theorem to particle filtering of discretely observed continuous-time non-linear systems
• Improved bridge constructs for stochastic differential equations
• Multilevel Sequential Monte Carlo with Dimension-Independent Likelihood-Informed Proposals

Cited In (11)

• Multilevel ensemble Kalman filtering for spatio-temporal processes
• Optimal parameter estimation for linear SPDEs from multiple measurements
• Accuracy of Some Approximate Gaussian Filters for the Navier--Stokes Equation in the Presence of Model Error
• Splitting-up spectral method for nonlinear filtering problems with correlation noises
• A Lagged Particle Filter for Stable Filtering of Certain High-Dimensional State-Space Models
• Advanced Multilevel Monte Carlo Methods
• A fast particle-based approach for calibrating a 3-D model of the Antarctic ice sheet
• Data assimilation: The Schrödinger perspective
• Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation
• An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations
• Multiscale modeling and analysis for some special additive noises driven stochastic partial differential equations

Uses Software

• EnKF

This page was built for publication: Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5745136)