摘要：Convective self-aggregation is a modelling paradigm for convective rain cell organisation over a constant-temperature tropical sea surface. This set-up can give rise to cloud clusters developing over timescales of weeks. In reality, sea-surface temperatures do oscillate diurnally, affecting the atmospheric state and influencing rain rates significantly. Over land, surface temperatures vary more strongly. Here, we carry out a suite of cloud-resolving numerical experiments, and find that qualitatively different dynamics emerge from modest surface temperature oscillations: while the spatial distribution of rainfall is homogeneous during the first day, already on the second day, the rain field is firmly structured. In later days, this clustering becomes stronger and alternates from day to day. We show that these features are robust to changes in resolution, domain size and mean surface temperature, but can be removed by a reduction of the amplitude of diurnal surface temperature oscillation, suggesting a transition from a random to a clustered state. Maximal clustering occurs at a scale of \({l}_{\max }\approx 180\ {\rm{km}}\), which we relate to the emergence of mesoscale convective systems. At \({l}_{\max }\), rainfall is strongly enhanced and far exceeds the rainfall expected at random. Simple conceptual modelling helps interpret the transition to clustering, which is driven by the formation of mesoscale convective systems, and brings about day-to-day moisture oscillations. Our results may help clarify how continental extremes build up, and how cloud clustering over the tropical ocean could emerge as an instance of spontaneous symmetry breaking at timescales much faster than in conventional radiative–convective equilibrium self-aggregation.
