Home > Research > Publications & Outputs > Particle Filters and Data Assimilation

Electronic data

  • 1709.04196v1

    Accepted author manuscript, 678 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

Particle Filters and Data Assimilation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Particle Filters and Data Assimilation. / Fearnhead, Paul; Künsch, Hans.
In: Annual Review of Statistics and Its Application, Vol. 5, 03.2018, p. 421-449.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Fearnhead, P & Künsch, H 2018, 'Particle Filters and Data Assimilation', Annual Review of Statistics and Its Application, vol. 5, pp. 421-449. https://doi.org/10.1146/annurev-statistics-031017-100232

APA

Fearnhead, P., & Künsch, H. (2018). Particle Filters and Data Assimilation. Annual Review of Statistics and Its Application, 5, 421-449. https://doi.org/10.1146/annurev-statistics-031017-100232

Vancouver

Fearnhead P, Künsch H. Particle Filters and Data Assimilation. Annual Review of Statistics and Its Application. 2018 Mar;5:421-449. Epub 2017 Dec 8. doi: 10.1146/annurev-statistics-031017-100232

Author

Fearnhead, Paul ; Künsch, Hans. / Particle Filters and Data Assimilation. In: Annual Review of Statistics and Its Application. 2018 ; Vol. 5. pp. 421-449.

Bibtex

@article{9bec6bd1979e4bd8bffb736dccf8e46a,
title = "Particle Filters and Data Assimilation",
abstract = "State-space models can be used to incorporate subject knowledge on the underlying dynamics of a time series by the introduction of a latent Markov state-process. A user can specify the dynamics of this process together with how the state relates to partial and noisy observations that have been made. Inference and prediction then involves solving a challenging inverse problem: calculating the conditional distribution of quantities of interest given the observations. This article reviews Monte Carlo algorithms for solving this inverse problem, covering methods based on the particle filter and the ensemble Kalman filter. We discuss the challenges posed by models with high-dimensional states, joint estimation of parameters and the state, and inference for the history of the state process. We also point out some potential new developments which will be important for tackling cutting-edge filtering applications.",
keywords = "stat.CO, stat.AP",
author = "Paul Fearnhead and Hans K{\"u}nsch",
year = "2018",
month = mar,
doi = "10.1146/annurev-statistics-031017-100232",
language = "English",
volume = "5",
pages = "421--449",
journal = "Annual Review of Statistics and Its Application",
issn = "2326-8298",
publisher = "Annual Reviews Inc.",

}

RIS

TY - JOUR

T1 - Particle Filters and Data Assimilation

AU - Fearnhead, Paul

AU - Künsch, Hans

PY - 2018/3

Y1 - 2018/3

N2 - State-space models can be used to incorporate subject knowledge on the underlying dynamics of a time series by the introduction of a latent Markov state-process. A user can specify the dynamics of this process together with how the state relates to partial and noisy observations that have been made. Inference and prediction then involves solving a challenging inverse problem: calculating the conditional distribution of quantities of interest given the observations. This article reviews Monte Carlo algorithms for solving this inverse problem, covering methods based on the particle filter and the ensemble Kalman filter. We discuss the challenges posed by models with high-dimensional states, joint estimation of parameters and the state, and inference for the history of the state process. We also point out some potential new developments which will be important for tackling cutting-edge filtering applications.

AB - State-space models can be used to incorporate subject knowledge on the underlying dynamics of a time series by the introduction of a latent Markov state-process. A user can specify the dynamics of this process together with how the state relates to partial and noisy observations that have been made. Inference and prediction then involves solving a challenging inverse problem: calculating the conditional distribution of quantities of interest given the observations. This article reviews Monte Carlo algorithms for solving this inverse problem, covering methods based on the particle filter and the ensemble Kalman filter. We discuss the challenges posed by models with high-dimensional states, joint estimation of parameters and the state, and inference for the history of the state process. We also point out some potential new developments which will be important for tackling cutting-edge filtering applications.

KW - stat.CO

KW - stat.AP

U2 - 10.1146/annurev-statistics-031017-100232

DO - 10.1146/annurev-statistics-031017-100232

M3 - Journal article

VL - 5

SP - 421

EP - 449

JO - Annual Review of Statistics and Its Application

JF - Annual Review of Statistics and Its Application

SN - 2326-8298

ER -