Contribution of expert aggregation to temperature prediction part I

TL;DR

This paper introduces a deterministic temperature prediction method using Expert Aggregation strategies, demonstrating improvements over traditional NWP models and analyzing various EA approaches' effectiveness and limitations.

Contribution

It proposes a novel application of Expert Aggregation for deterministic temperature prediction, enhancing accuracy and adaptability over existing NWP models.

Findings

EA strategies improve temperature prediction accuracy

EA methods are adaptive to model changes

Comparison reveals strengths and limitations of different EA approaches

Abstract

Many Numerical Weather Prediction (NWP) models and their associated Model Output Statistics (MOS) are available. Combining all of these predictions in an optimal way is however not straightforward. This can be achieved thanks to Expert Aggregation (EA) [Cesa-Bianchi and Lugosi, 2006, Gaillard et al., 2014, Wintenberger, 2024] which has many advantages, such as being online, being adaptive to model changes and having theoretical guarantees. Hence, in this paper, we propose a method for making deterministic temperature predictions with EA strategies and show how this can improve temperature predictions, even those of post processed NWP models. We also compare different EA strategies in various settings and discuss certain limitations.