Robust detection and attribution of climate change under interventions

TL;DR

This paper introduces a supervised learning method using anchor regression for robust climate change detection and attribution, effectively handling interventions on climate drivers to improve reliability.

Contribution

It presents a novel distributionally-robust approach based on anchor regression for climate change detection and attribution under interventions, unifying hypothesis testing within a statistical framework.

Findings

Robust prediction of CO2 forcing from temperature patterns under solar forcing interventions.

Effective attribution to greenhouse gases and aerosols while accounting for interventions.

Robustness constraints improve detection and attribution accuracy.

Abstract

Fingerprints are key tools in climate change detection and attribution (D&A) that are used to determine whether changes in observations are different from internal climate variability (detection), and whether observed changes can be assigned to specific external drivers (attribution). We propose a direct D&A approach based on supervised learning to extract fingerprints that lead to robust predictions under relevant interventions on exogenous variables, i.e., climate drivers other than the target. We employ anchor regression, a distributionally-robust statistical learning method inspired by causal inference that extrapolates well to perturbed data under the interventions considered. The residuals from the prediction achieve either uncorrelatedness or mean independence with the exogenous variables, thus guaranteeing robustness. We define D&A as a unified hypothesis testing framework that relies on the same statistical model but uses different targets and test statistics. In the experiments, we first show that the CO2 forcing can be robustly predicted from temperature spatial patterns under strong interventions on the solar forcing. Second, we illustrate attribution to the greenhouse gases and aerosols while protecting against interventions on the aerosols and CO2 forcing, respectively. Our study shows that incorporating robustness constraints against relevant interventions may significantly benefit detection and attribution of climate change.