A Framework for Multi-Model Ensembling

作者：Berliner L Mark^*; Brynjarsdottir Jenny

来源：SIAM-ASA Journal on Uncertainty Quantification, 2016, 4(1): 902-923.

DOI：10.1137/130928339

• climate change
• computer models
• dimension reduction
• importance sampling
• kernel density estimation
• uncertainty quantification

As reliance on computer modeling increases, scientists and engineers often produce ensembles of model runs from multiple models. Combining such multi-model ensembles while managing uncertainties is a challenging problem. We embed the problem into a Bayesian framework. Specifically, a Bayesian is to update prior beliefs based on information regarding the probability distributions from a collection of experts. These experts may be individuals, research centers, computer modeling teams, etc. In this article we use one well-known approach to combining probability distributions, the so-called linear opinion pool, to provide a basis for suggesting approaches for processing multi-model ensembles. First, had the experts' probability distributions been available, we consider treating their combination as if it is a likelihood for the quantities of interest and combine it with our prior distribution by formal application of Bayes' theorem to produce our posterior distribution. Second, we will act as if the ensembles obtained from each model are samples from the corresponding expert's probability distribution. We consider approaches to using the ensembles to reflect our posterior, either by modeling or estimating it or by using importance sampling techniques to convert the ensembles to represent probability weighted samples from our posterior distribution. We illustrate these approaches in the analysis of a multi-model ensemble of projections of global annual surface temperatures through the year 2099. The analyses incorporate a suggestion for using importance sampling in the presence of high dimensions.

• 出版日期2016