Name
Abstract | ||
|---|---|---|
Ensemble Kalman filter (EnKF) has proven successful in assimilating observations of large-scale dynamical systems, such as the atmosphere, into computer simulations for better predictability. Due to the fact that a limited-size ensemble of model states is used, sampling errors accumulate, and manifest themselves as long-range spurious correlations, leading to filter divergence. This effect is alleviated in practice by applying covariance localization. This work investigates the possibility of using machine learning algorithms to automatically tune the parameters of the covariance localization step of ensemble filters. Numerical experiments carried out with the Lorenz-96 model reveal the potential of the proposed machine learning approaches. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/978-3-030-22747-0_16 | COMPUTATIONAL SCIENCE - ICCS 2019, PT IV |
Keywords | Field | DocType |
Data assimilation, EnKF, Covariance localization, Machine learning | Predictability,Computer science,Sampling error,Dynamical systems theory,Artificial intelligence,Data assimilation,Ensemble Kalman filter,Spurious relationship,Machine learning,Covariance | Conference |
Volume | ISSN | Citations |
11539 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Azam S. Zavar Moosavi | 1 | 14 | 4.12 |
| Ahmed Attia | 2 | 13 | 3.80 |
| Adrian Sandu | 3 | 325 | 58.93 |