Exploring the contribution of low‐frequency internal variability modes to global mean sea surface temperature variability based on large ensembles

Abstract

Based on three large ensemble (LE) historical simulations, this study explored the contribution of low‐frequency internal variability (IV) modes to global mean sea surface temperature anomaly (GmSST) during 1920–2010. The dominant contributions of low‐frequency IV modes to GmSST in the three large ensembles are quite different. The low‐frequency IV modes in the Indo‐Pacific Ocean (i.e., IPO and IOBW) dominate the low‐frequency GmSST signal for the CESM2 and MPI LEs (the ensemble median contribution value reaches 70%–80%), while the low‐frequency IV modes in the North Atlantic dominate for the FGOALS‐g3 LE (contribute more than 50%). CESM2 LE and MPI LE can reasonably reproduce the impact of low‐frequency modes in the Indo‐Pacific ocean as observed, but FGOALS‐g3 LE underestimates this impact and overestimates the extratropical impact (on GmSST) of the North Atlantic. After removing the external forcing, it still retains the excessive signs in low‐frequency IV modes in FGOALS‐g3 LE over the North Atlantic. Furthermore, we used a pattern adjustment approach to revise the surplus effect in the North Atlantic. After revision, the contribution of decadal IVs in the North Atlantic to GmSST is reduced by 30%. Meanwhile, the tropical contribution in the Indo‐Pacific Ocean is increased and that is closer to the observed one. This approach can be employed to revise the weak or strong IV signals in other regions or LEs, which is meaningful for reducing the uncertainty of IV signals.