Articles | Volume 8, issue 2
https://doi.org/10.5194/esd-8-429-2017
https://doi.org/10.5194/esd-8-429-2017
Research article
 | 
28 Jun 2017
Research article |  | 28 Jun 2017

An efficient training scheme for supermodels

Francine J. Schevenhoven and Frank M. Selten

Abstract. Weather and climate models have improved steadily over time as witnessed by objective skill scores, although significant model errors remain. Given these imperfect models, predictions might be improved by combining them dynamically into a so-called supermodel. In this paper a new training scheme to construct such a supermodel is explored using a technique called cross pollination in time (CPT). In the CPT approach the models exchange states during the prediction. The number of possible predictions grows quickly with time, and a strategy to retain only a small number of predictions, called pruning, needs to be developed. The method is explored using low-order dynamical systems and applied to a global atmospheric model. The results indicate that the CPT training is efficient and leads to a supermodel with improved forecast quality as compared to the individual models. Due to its computational efficiency, the technique is suited for application to state-of-the art high-dimensional weather and climate models.

Download
Short summary
Weather and climate models have improved steadily over time, but the models remain imperfect. Given these imperfect models, predictions might be improved by combining the models into a so-called “supermodel”. In this paper we show a new method to construct such a supermodel. The results indicate that the supermodel has superior forecast quality compared to the individual models.
Altmetrics
Final-revised paper
Preprint