Quantifying uncertainty in climate projections with conformal ensembles

TL;DR

This paper introduces conformal ensembles, a novel method for quantifying climate projection uncertainty by integrating observational data with model ensembles, providing more reliable and interpretable uncertainty estimates.

Contribution

The paper presents conformal ensembles, a new approach that improves climate uncertainty quantification by combining observational data with model ensembles using conformal prediction techniques.

Findings

CE outperforms existing methods in uncertainty quantification across various scales.

CE provides statistically rigorous and physically consistent projections.

CE is computationally efficient and robust across different variables and analysis methods.

Abstract

Ensembles of General Circulation Models (GCMs) are the primary tools for investigating climate sensitivity, projecting future climate states, and quantifying uncertainty. GCM ensembles are subject to substantial uncertainty due to model inadequacies, resolution limits, internal variability, and inter-model variability, meaning rigorous climate risk assessments and informed decision-making require reliable and accurate uncertainty quantification (UQ). We introduce conformal ensembles (CE), a new approach to climate UQ that quantifies and constrains projection uncertainty with conformal prediction sets and observational data. CE seamlessly integrates climate model ensembles and observational data across a range of scales to generate statistically rigorous, easy-to-interpret uncertainty estimates. CE can be applied to any climatic variable using any ensemble analysis method and outperforms existing inter-model variability methods in uncertainty quantification across all time horizons and most spatial locations under SSP2-4.5. CE is also computationally efficient, requires minimal assumptions, and is highly robust to the conformity measure. Experiments show that it is effective when conditioning future projections on historical reanalysis data compared with standard ensemble averaging approaches, yielding more physically consistent projections.