Effects of rotation and mid-troposphere moisture on organized convection and convectively coupled gravity waves

Atmospheric convection has the striking capability to organize itself into a hierarchy of cloud clusters and super-clusters on scales ranging from the convective cell of a few kilometres to planetary scale disturbances such as the Madden–Julian oscillation. It is widely accepted that this phenomenon is due in large part to the two-way coupling between convective processes and equatorially trapped waves and planetary scale flows in general. However, the physical mechanisms responsible for this multiscale organization and the associated across-scale interactions are poorly understood. The two main peculiarities of the tropics are the vanishing of the Coriolis force at the equator and the abundance of mid-level moisture. Here we test the effect of these two physical properties on the organization of convection and its interaction with gravity waves in a simplified primitive equation model for flows parallel to the equator. Convection is represented by deterministic as well as stochastic multicloud models that are known to represent organized convection and convectively coupled waves quite well. It is found here that both planetary rotation and mid-troposphere moisture are important players in the diminishing of organized convection and convectively coupled gravity wave activity in the subtropics and mid-latitudes. The meridional mean circulation increases with latitude while the mean zonal circulation is much shallower and is dominated by mid-level jets, reminiscent of a second baroclinic mode circulation associated with a congestus mode instability in the model. This is consistent with the observed shallow Hadley and Walker circulations accompanied by congestus cloud decks in the higher latitude tropics and sub-tropics. Moreover, deep convection activity in the stochastic model simulations becomes very patchy and unorganized as the computational domain is pushed towards the subtropics and mid-latitudes. This is consistent with previous work based on cloud resolving modeling simulations on smaller domains.