Effects of the Madden–Julian Oscillation on 2-m air temperature prediction over China during boreal winter in the S2S database

The reforecast of 11 models in the sub-seasonal to seasonal (S2S) prediction project has been analyzed to investigate the effects of the Madden–Julian Oscillation (MJO) on the prediction skill of winter 2-m air temperature (T2M) over China. Most of the S2S models have useful prediction skills (correlation skill ≥ 0.5) before pentads 3 and 4. ECMWF model can possess a good prediction skill for almost four pentads and perform the best among the 11 models. ECCC and ECMWF models have more reliable ensemble prediction and better ensemble strategies than the other models. All the models tend to have lower T2M prediction skill over the Tibetan Plateau than that over the other regions of China. Moreover, initial state and model resolution have important influences on S2S prediction skill. In most of the models at pentads 3 and 4, T2M prediction skill of forecast with MJO at initial time is significantly higher than that without over parts of China. However, the spatial distributions of the prediction skill differences due to MJO are not consistent among the 11 models. This indicates that there is an uncertainty of the effects of MJO on T2M prediction over China at pentads 3 and 4. Planetary-scale teleconnection pattern excited by MJO over the Northern Hemisphere is the possible reason for the effect of MJO on T2M prediction skill. Because most of the models can maintain this teleconnection pattern for 3–4 forecast pentads, MJO can affect the atmospheric circulation over China during this period, and improve the T2M prediction skill in the models. This finding suggests that the prediction of winter T2M over China initialized with MJO can be more skillful at pentads 3 and 4 than that without MJO in the initial conditions.