Abstract Earth's climate stability, characterized by the global radiative feedback parameter , varies decadally due to changing surface temperature patterns. Recent variations in 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 up to 2025. We find that reached a minimum (maximum stability) around the mid 1990s (−3 Wm −2 /K), but has since weakened significantly (−2 Wm −2 /K). We confirm these results with climate model simulations extended to 2022. The recent weakening is not significantly affected by El Niño 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.
Loon et al. (Tue,) studied this question.