A barycenter-based approach for the multi-model ensembling of subseasonal forecasts

TL;DR

This paper introduces a novel barycenter-based framework for multi-model ensemble forecasting, comparing L2 and Wasserstein barycenters to improve the combination of probabilistic subseasonal forecasts.

Contribution

It formulates multi-model ensemble forecasts as barycenters of probability distributions, highlighting the advantages of Wasserstein barycenters in preserving geometric properties.

Findings

Wasserstein barycenter performs better more frequently in forecast accuracy.

L2 barycenter has a larger ensemble spread, indicating under-confidence.

Both methods have similar average CRPS performance.

Abstract

Ensemble forecasts and their combination are examined from the perspective of probability spaces. Manipulating ensemble forecasts as discrete probability distributions, multi-model ensemble (MME) forecasts are reformulated as barycenters of these distributions. We consider two barycenters, each defined with respect to a different distance metric: the L2 barycenter, which correspond to the traditional pooling method, and the Wasserstein barycenter, which better preserves certain geometric properties of the input ensemble distributions. As a proof of concept, we apply the L2 and Wasserstein barycenters to the combination of four models from the Subseasonal to Seasonal (S2S) prediction project database. Their performance is evaluated for the prediction of weekly 2m temperature, 10m wind speed, and 500hPa geopotential height over European winters. By construction, both barycenter-based MMEs have the same ensemble mean, but differ in their representation of the forecast uncertainty. Notably, the L2 barycenter has a larger ensemble spread, making it more prone to under-confidence. While both methods perform similarly on average in terms of the Continuous Ranked Probability Score (CRPS), the Wasserstein barycenter performs better more frequently.