Decadal climate predictions using sequential learning algorithms

TL;DR

This paper demonstrates that sequential learning algorithms can effectively improve decadal climate predictions by reducing forecast errors and uncertainties across multiple climate variables.

Contribution

The study introduces and compares three sequential learning algorithms for weighting climate models, showing their superiority over traditional methods in decadal climate prediction.

Findings

SLAs outperform equal weighting and linear regression in accuracy

Significant reduction in forecast uncertainties with SLAs

Proposed SLA is highly suitable for decadal climate predictions

Abstract

Ensembles of climate models are commonly used to improve climate predictions and assess the uncertainties associated with them. Weighting the models according to their performances holds the promise of further improving their predictions. Here, we use an ensemble of decadal climate predictions to demonstrate the ability of sequential learning algorithms (SLAs) to reduce the forecast errors and reduce the uncertainties. Three different SLAs are considered, and their performances are compared with those of an equally weighted ensemble, a linear regression and the climatology. Predictions of four different variables--the surface temperature, the zonal and meridional wind, and pressure--are considered. The spatial distributions of the performances are presented, and the statistical significance of the improvements achieved by the SLAs is tested. Based on the performances of the SLAs, we propose one to be highly suitable for the improvement of decadal climate predictions.