摘要：Tropical rainfall is mostly convective and its subseasonal-to-seasonal (S2S) prediction remains challenging. We show that state-of-art model forecast skill 3 + 4 weeks ahead is systematically lower over land than ocean, which is matched by a similar land-ocean contrast in the spatial scales of observed biweekly rainfall anomalies. Regional differences in predictability are then interpreted using observed characteristics of daily rainfall (wet-patch size, mean intensity as well as the strength of local S2S modes of rainfall variation), and classified into six S2S predictability types. Both forecast skill and spatial scales are reduced over the continents, either because daily rainfall patches are small and poorly organized by S2S modes of variation (as over equatorial and northern tropical Africa), or where the daily mean intensity is very high (as over South and SE Asia). Forecast skill and spatial scales are largest where daily rainfall is synchronized by intraseasonal (such as the Madden-Julian Oscillation) as well as interannual ocean-atmosphere modes of variation (such as El Niño-Southern Oscillation), especially over northern Australia and parts of the Maritime Continent, and over parts of eastern, southern Africa and northeast South America. The oceans exhibit the highest skill and largest spatial scales, especially where interannual (central equatorial Pacific) or intraseasonal (central and eastern Tropical Indian Ocean and Western Pacific) variability is largest. These results provide a relevant regional typology of the potential drivers and controls on S2S predictability of tropical rainfall, informing intrinsic limits and possible improvements toward useful S2S climate prediction at regional scale.
