Quantifying Sources of Subseasonal Prediction Skill in CESM2
There are many unanswered questions with regard to sources of sub-seasonal predictability. There is evidence that predictability on subseasonal timescales comes from a combination of atmosphere, land, and ocean initial conditions, however this has never been quantified. Using a unique suite of subseasonal forecast experiments, we quantify the respective roles of atmosphere, land, and ocean initial conditions on sub-seasonal prediction skill over land.
The study reveals unexpected findings. It showed that the majority of prediction skill for global surface temperature in weeks 3–4 comes from the atmosphere, while ocean initial conditions become important after week 4, especially in the Tropics. In the CESM2 subseasonal prediction system, the land initial state does not contribute to surface temperature prediction skill in weeks 3–6 and climatological land conditions lead to higher skill, disagreeing with our current understanding. However, land-atmosphere coupling is important in week 1. Subseasonal precipitation prediction skill also comes primarily from the atmospheric initial condition, except for the Tropics, where after week 4 the ocean state is more important.
We have performed here a unique set of subseasonal reforecast experiments with CESM2 quantifying the respective roles of atmosphere, land, and ocean initial conditions on subseasonal prediction skill over land. Contrary to popular belief, we find that the land in CESM2, does not contribute much to subseasonal prediction skill over land; Most of the contribution comes from the atmospheric initial state. The role of the ocean's initial state becomes important in Week 4.