资源环境科技发展态势分析平台

Low-frequency internal climate variability (ICV) plays an important role in modulating global surface temperature, regional climate, and climate extremes. However, it has not been completely characterized in the instrumental record and in the Coupled Model Intercomparison Project phase 5 (CMIP5) model ensemble. In this study, the surface temperature ICV of the North Pacific (NP), North Atlantic (NA), and Northern Hemisphere (NH) in the instrumental record and historical CMIP5 all-forcing simulations is isolated using a semiempirical method wherein the CMIP5 ensemble mean is applied as the external forcing signal and removed from each time series. Comparison of ICV signals derived from this semiempirical method as well as from analysis of ICV in CMIP5 preindustrial control runs reveals disagreement in the spatial pattern and amplitude between models and instrumental data on multidecadal time scales (>20 yr). Analysis of the amplitude of total variability and the ICV in the models and instrumental data indicates that the models underestimate ICV amplitude on low-frequency time scales (>20 yr in the NA; >40 yr in the NP), while agreement is found in the NH variability. A multiple linear regression analysis of ICV in the instrumental record shows that variability in the NP drives decadal-to-interdecadal variability in the NH, whereas the NA drives multidecadal variability in the NH. Analysis of the CMIP5 historical simulations does not reveal such a relationship, indicating model limitations in simulating ICV. These findings demonstrate the need to better characterize low-frequency ICV, which may help improve attribution and decadal prediction.