Filtering nonlinear dynamical systems with linear stochastic models

DOI10.1088/0951-7715/21/6/008zbMath1147.93411MaRDI QIDQ3507964

Andrew J. Majda, John Harlim

Publication date: 24 June 2008

Published in: Nonlinearity (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/c3ed4ff44f42a02478cf9667e34adefd7b5ccd0a

zbMATH Keywords

computational efficiency; Kalman filters; filter robustness; L-96 model; radical filtering approach; relatively low dimensional toy model

Mathematics Subject Classification ID

62M20: Inference from stochastic processes and prediction

93E11: Filtering in stochastic control theory

65C20: Probabilistic models, generic numerical methods in probability and statistics

93C05: Linear systems in control theory

74S25: Spectral and related methods applied to problems in solid mechanics

93E03: Stochastic systems in control theory (general)

62L12: Sequential estimation

Related Items

Accuracy of Some Approximate Gaussian Filters for the Navier--Stokes Equation in the Presence of Model Error, Dynamic Stochastic Superresolution of sparsely observed turbulent systems, Filtering nonlinear spatio-temporal chaos with autoregressive linear stochastic models, On completeness of quadratic systems, An algebraic method for constructing stable and consistent autoregressive filters, Mathematical strategies for filtering complex systems: Regularly spaced sparse observations, Test models for improving filtering with model errors through stochastic parameter estimation, Improving filtering and prediction of spatially extended turbulent systems with model errors through stochastic parameter estimation, Accuracy and stability of filters for dissipative PDEs, Parallel probabilistic graphical model approach for nonparametric Bayesian inference, Reduced one-dimensional models for wave turbulence system, Multi-model communication and data assimilation for mitigating model error and improving forecasts, Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data, An object-based model for convective cold pool dynamics, Mathematical test criteria for filtering complex systems: Plentiful observations, Particle filtering in high-dimensional chaotic systems

Uses Software

• EnKF