What the collapse of the ensemble Kalman filter tells us about particle filters
The ensemble Kalman filter (EnKF) is a reliable data assimilation tool for high-dimensional meteorological problems. On the other hand, the EnKF can be interpreted as a particle filter, and particle filters (PF) collapse in high-dimensional problems. We explain that these seemingly contradictory sta...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2017-01-01
|
| Series: | Tellus: Series A, Dynamic Meteorology and Oceanography |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/16000870.2017.1283809 |
| id |
doaj-a091d72fd295456ca5ff0e4349ed252e |
|---|---|
| record_format |
Article |
| spelling |
doaj-a091d72fd295456ca5ff0e4349ed252e2020-11-25T01:49:09ZengTaylor & Francis GroupTellus: Series A, Dynamic Meteorology and Oceanography1600-08702017-01-0169110.1080/16000870.2017.12838091283809What the collapse of the ensemble Kalman filter tells us about particle filtersMatthias Morzfeld0Daniel Hodyss1Chris Snyder2University of ArizonaNaval Research LaboratoryNational Center for Atmospheric ResearchThe ensemble Kalman filter (EnKF) is a reliable data assimilation tool for high-dimensional meteorological problems. On the other hand, the EnKF can be interpreted as a particle filter, and particle filters (PF) collapse in high-dimensional problems. We explain that these seemingly contradictory statements offer insights about how PF function in certain high-dimensional problems, and in particular support recent efforts in meteorology to ‘localize’ particle filters, i.e. to restrict the influence of an observation to its neighbourhood.http://dx.doi.org/10.1080/16000870.2017.1283809ensemble Kalman filterparticle filtercollapse of particle filters |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Matthias Morzfeld Daniel Hodyss Chris Snyder |
| spellingShingle |
Matthias Morzfeld Daniel Hodyss Chris Snyder What the collapse of the ensemble Kalman filter tells us about particle filters Tellus: Series A, Dynamic Meteorology and Oceanography ensemble Kalman filter particle filter collapse of particle filters |
| author_facet |
Matthias Morzfeld Daniel Hodyss Chris Snyder |
| author_sort |
Matthias Morzfeld |
| title |
What the collapse of the ensemble Kalman filter tells us about particle filters |
| title_short |
What the collapse of the ensemble Kalman filter tells us about particle filters |
| title_full |
What the collapse of the ensemble Kalman filter tells us about particle filters |
| title_fullStr |
What the collapse of the ensemble Kalman filter tells us about particle filters |
| title_full_unstemmed |
What the collapse of the ensemble Kalman filter tells us about particle filters |
| title_sort |
what the collapse of the ensemble kalman filter tells us about particle filters |
| publisher |
Taylor & Francis Group |
| series |
Tellus: Series A, Dynamic Meteorology and Oceanography |
| issn |
1600-0870 |
| publishDate |
2017-01-01 |
| description |
The ensemble Kalman filter (EnKF) is a reliable data assimilation tool for high-dimensional meteorological problems. On the other hand, the EnKF can be interpreted as a particle filter, and particle filters (PF) collapse in high-dimensional problems. We explain that these seemingly contradictory statements offer insights about how PF function in certain high-dimensional problems, and in particular support recent efforts in meteorology to ‘localize’ particle filters, i.e. to restrict the influence of an observation to its neighbourhood. |
| topic |
ensemble Kalman filter particle filter collapse of particle filters |
| url |
http://dx.doi.org/10.1080/16000870.2017.1283809 |
| work_keys_str_mv |
AT matthiasmorzfeld whatthecollapseoftheensemblekalmanfiltertellsusaboutparticlefilters AT danielhodyss whatthecollapseoftheensemblekalmanfiltertellsusaboutparticlefilters AT chrissnyder whatthecollapseoftheensemblekalmanfiltertellsusaboutparticlefilters |
| _version_ |
1725008565441134592 |