Low-level easterly winds encircling Antarctica help drive coastal currents which modify transport of circumpolar deep water to ice shelves, and the formation and distribution of sea ice. Reanalysis datasets are especially important at high southern latitudes where observations are few. Here, we investigate the representation of the mean state and short-term variability of coastal easterlies in three recent reanalyses, ERA5, MERRA-2 and JRA-55. Reanalysed winds are compared with summertime marine near-surface wind observations from the Advanced Scatterometer (ASCAT) and surface and upper air measurements from coastal stations. Reanalysis coastal easterlies correlate highly with ASCAT ( r = 0.91, 0.89 and 0.85 for ERA5, MERRA-2 and JRA-55, respectively) but notable wind speed biases are found close to the coastal margins, especially near complex orography and at high wind speeds. To characterise short-term variability, 12-hourly reanalysis and coastal station winds are composited using self-organising maps (SOMs), which cluster timesteps under similar synoptic and mesoscale influences. Reanalysis performance is sensitive to the flow configuration at stations near steep coastal slopes, where they fail to capture the magnitude of near-surface wind speed variability when synoptic forcing is weak and conditions favour katabatic forcing. ERA5 exhibits the best overall performance, has more realistic orography, and a more realistic jet structure and temperature profile. These results demonstrate the regime behaviour of Antarctica's coastal winds and indicate important features of the coastal winds which are not well characterised by reanalysis datasets.
