Use this URL to cite or link to this record in EThOS:
Title: Methods of likelihood based inference for constructing stochastic climate models
Author: Peavoy, Daniel
Awarding Body: University of Warwick
Current Institution: University of Warwick
Date of Award: 2012
Availability of Full Text:
Access from EThOS:
Access from Institution:
This thesis is about the construction of low dimensional diffusion models of climate variables. It assesses the predictive skill of models derived from a principled averaging procedure and a purely empirical approach. The averaging procedure starts from the equations for the original system then approximates the \weather" variables by a stochastic process. They are then averaged with respect to their invariant measure. This assumes that they equilibriate much faster than the climate variables. The empirical approach argues for a very general model form, then parameters are estimated using likelihood based inference for Stochastic Differential Equations. This is computationally demanding and relies upon Markov Chain Monte Carlo methods. A large part of this thesis is focused upon techniques to improve the efficiency of these algorithms. The empirical approach works well on simple one dimensional models but performs poorly on multivariate problems due to the rapid increase in unknown parameters. The averaging procedure is skillful in multivariate problems but is sensitive to lack of complete time scale separation in the system. In conclusion, the averaging procedure is better and can be improved by estimating parameters in a principled way based on the likelihood function and by including a latent noise process in the model.
Supervisor: Not available Sponsor: Engineering and Physical Sciences Research Council (EPSRC) ; Natural Environment Research Council (Great Britain) (NERC)
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: QA Mathematics ; QC Physics