Recent Weakening of the Global Radiative Feedback

TL;DR

This study uses neural networks and climate data to track recent changes in Earth's climate feedback, revealing a weakening trend since the mid-1990s driven by subtropical Pacific warming.

Contribution

It introduces a neural network-based method to estimate climate feedback variations up to 2025 using observational data, extending beyond typical model simulation periods.

Findings

$$ feedback parameter reached a minimum in the mid 1990s.

Recent weakening of $$ is confirmed by extended climate model simulations.

Subtropical Northeast Pacific warming is a key driver of feedback weakening.

Abstract

Earth's climate stability, characterized by the global radiative feedback parameter ($\lambda$), varies decadally due to changing surface temperature patterns. Recent variations in $\lambda$ are poorly understood as coordinated model simulations typically end in 2014. We apply a convolutional neural network trained on climate model simulations to observation-based surface temperature reconstructions to estimate variations in $\lambda$ up to 2025. We find that $\lambda$ reached a minimum (maximum stability) around the mid 1990s ($\lambda\simeq -3 {\rm Wm^{-2}/K}$), but has since weakened significantly ($\lambda\simeq -2\, {\rm Wm^{-2}/K}$). We confirm these results with climate model simulations extended to 2022. The recent $\lambda$ weakening is not significantly affected by El Ni\~no Southern Oscillation or Pacific Decadal Oscillation. Attribution reveals that warming in the subtropical Northeast Pacific is an important driver of the recently weakened feedback, confirmed by targeted experiments in E3SMv2. Our approach enables near real-time monitoring of Earth's climate stability.