|
Titel |
Optimal model-free prediction from multivariate time series |
VerfasserIn |
Jakob Runge, Reik V. Donner, Jürgen Kurths |
Konferenz |
EGU General Assembly 2015
|
Medientyp |
Artikel
|
Sprache |
Englisch
|
Digitales Dokument |
PDF |
Erschienen |
In: GRA - Volume 17 (2015) |
Datensatznummer |
250112277
|
Publikation (Nr.) |
EGU/EGU2015-12425.pdf |
|
|
|
Zusammenfassung |
Forecasting a complex system's time evolution constitutes a challenging problem, especially if the governing physical equations are unknown or too complex to be simulated with first-principle models.
Here a model-free prediction scheme based on the observed multivariate time series is discussed. It efficiently overcomes the curse of dimensionality in finding good predictors from large data sets and yields information-theoretically optimal predictors.
The practical performance of the prediction scheme is demonstrated on multivariate nonlinear stochastic delay processes and in an application to an index of El Nino-Southern Oscillation. |
|
|
|
|