A Gaussian mixture ensemble transform filter for vector observations
The ensemble Kalman filter relies on a Gaussian approximation being a reasonably accurate representation of the filtering distribution. Reich recently introduced a Gaussian mixture ensemble transform filter which can address scenarios where the prior can be modeled using a Gaussian mixture. Reichs d...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2013
|
| _version_ | 1797078987484168192 |
|---|---|
| author | Nannuru, S Coatesa, M Doucet, A |
| author_facet | Nannuru, S Coatesa, M Doucet, A |
| author_sort | Nannuru, S |
| collection | OXFORD |
| description | The ensemble Kalman filter relies on a Gaussian approximation being a reasonably accurate representation of the filtering distribution. Reich recently introduced a Gaussian mixture ensemble transform filter which can address scenarios where the prior can be modeled using a Gaussian mixture. Reichs derivation is suitable for a scalar measurement or a vector of uncorrelated measurements. We extend the derivation to the case of vector observations with arbitrary correlations. We illustrate through numerical simulation that implementation is challenging, because the filter is prone to instability. © 2013 SPIE. |
| first_indexed | 2024-03-07T00:39:13Z |
| format | Journal article |
| id | oxford-uuid:827778f9-b6ce-4c99-8e27-e2fa83f669aa |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T00:39:13Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | oxford-uuid:827778f9-b6ce-4c99-8e27-e2fa83f669aa2022-03-26T21:37:31ZA Gaussian mixture ensemble transform filter for vector observationsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:827778f9-b6ce-4c99-8e27-e2fa83f669aaEnglishSymplectic Elements at Oxford2013Nannuru, SCoatesa, MDoucet, AThe ensemble Kalman filter relies on a Gaussian approximation being a reasonably accurate representation of the filtering distribution. Reich recently introduced a Gaussian mixture ensemble transform filter which can address scenarios where the prior can be modeled using a Gaussian mixture. Reichs derivation is suitable for a scalar measurement or a vector of uncorrelated measurements. We extend the derivation to the case of vector observations with arbitrary correlations. We illustrate through numerical simulation that implementation is challenging, because the filter is prone to instability. © 2013 SPIE. |
| spellingShingle | Nannuru, S Coatesa, M Doucet, A A Gaussian mixture ensemble transform filter for vector observations |
| title | A Gaussian mixture ensemble transform filter for vector observations |
| title_full | A Gaussian mixture ensemble transform filter for vector observations |
| title_fullStr | A Gaussian mixture ensemble transform filter for vector observations |
| title_full_unstemmed | A Gaussian mixture ensemble transform filter for vector observations |
| title_short | A Gaussian mixture ensemble transform filter for vector observations |
| title_sort | gaussian mixture ensemble transform filter for vector observations |
| work_keys_str_mv | AT nannurus agaussianmixtureensembletransformfilterforvectorobservations AT coatesam agaussianmixtureensembletransformfilterforvectorobservations AT douceta agaussianmixtureensembletransformfilterforvectorobservations AT nannurus gaussianmixtureensembletransformfilterforvectorobservations AT coatesam gaussianmixtureensembletransformfilterforvectorobservations AT douceta gaussianmixtureensembletransformfilterforvectorobservations |