期刊名称：Journal of Advances in Modeling Earth Systems
电子版ISSN：1942-2466
出版年度：2020
卷号：12
期号：10
页码：1-20
DOI：10.1029/2020MS002165
出版社：John Wiley & Sons, Ltd.
摘要：The Radiative‐Convective Equilibrium Model Intercomparison Project (RCEMIP) consists of simulations at three fixed sea‐surface temperatures (SSTs: 295, 300, and 305 K) and thus allows for a calculation of the climate feedback parameter based on the change of the top‐of‐atmosphere radiation imbalance. Climate feedback parameters range widely across RCEMIP, roughly from − 6 to 3 W m −2 K −1 , particularly across general‐circulation models (GCMs) as well as global and large‐domain cloud‐resolving models (CRMs). Small‐domain CRMs and large‐eddy simulations have a smaller range of climate feedback parameters due to the absence of convective self‐aggregation. More than 70–80% of the intermodel spread in the climate feedback parameter can be explained by the combined temperature dependencies of convective aggregation and shallow cloud fraction. Low climate sensitivities are associated with an increase of shallow cloud fraction (increasing the planetary albedo) and/or an increase in convective aggregation with warming. An increase in aggregation is associated with an increase in outgoing longwave radiation, caused primarily by mid‐tropospheric drying, and secondarily by an expansion of subsidence regions. Climate sensitivity is neither dependent on the average amount of aggregation nor on changes in deep/anvil cloud fraction. GCMs have a lower overall climate sensitivity than CRMs because in most GCMs convective aggregation increases with warming, whereas in CRMs, convective aggregation shows no consistent temperature trend. Plain Language Abstract To determine how much Earth will warm in response to anthropogenic greenhouse gas emissions, we need to understand the atmospheric response to this forcing. The amount of warming in response to a given forcing is called climate sensitivity. Although global climate models are a useful tool to estimate climate sensitivity, estimates remain uncertain, in particular because the response of tropical clouds to warming is uncertain. The weakness of climate models is their coarse grid spacing, with which they cannot resolve important aspects of the weather like clouds and convection. In this study, we use a popular idealization for the tropics, the radiative‐convective equilibrium setup, to compare climate sensitivities across a wide range of models including global climate models and cloud‐resolving models. We find that more than 70–80% of variations in climate sensitivity across these models result from changes in shallow cloud fraction and changes in the spatial organization of convection with warming. Our results indicate that climate sensitivity might be underestimated by global climate models, in which the amount of spatial organization of convection mostly increases with warming, leading to low climate sensitivities, while the cloud‐resolving models show no consistent trend in spatial organization, and thus have higher climate sensitivities.
关键词：radiative‐convective equilibrium;climate sensitivity;convective self‐aggregation;cloud feedbacks;hierarchy of models;RCEMIP
