Simulation by CMIP5 models of the atlantic multidecadal oscillation and its climate impacts

This study focuses on the climatic impacts of the Atlantic Multidecadal Oscillation (AMO) as a mode of internal variability. Given the difficulties involved in excluding the effects of external forcing from internal variation, i.e., owing to the short record length of instrumental observations and historical simulations, we assess and compare the AMO and its related climatic impacts both in observations and in the "Pre-industrial" experiments of models participating in CMIP5. First, we evaluate the skill of the 25 CMIP5 models' "Historical" simulations in simulating the observational AMO, and find there is generally a considerable range of skill among them in this regard. Six of the models with higher skill relative to the other models are selected to investigate the AMO-related climate impacts, and it is found that their "Pre-industrial" simulations capture the essential features of the AMO. A positive AMO favors warmer surface temperature around the North Atlantic, and the Atlantic ITCZ shifts northward leading to more rainfall in the Sahel and less rainfall in Brazil. Furthermore, the results confirm the existence of a teleconnection between the AMO and East Asian surface temperature, as well as the late withdrawal of the Indian summer monsoon, during positive AMO phases. These connections could be mainly caused by internal climate variability. Opposite patterns are true for the negative phase of the AMO.