Numerical impacts on tracer transport: A proposed intercomparison test of Atmospheric General Circulation Models

The transport of trace gases by the atmospheric circulation plays an important role in the climate system and its response to external forcing. Transport presents a challenge for Atmospheric General Circulation Models (AGCMs), as errors in both the resolved circulation and the numerical representation of transport processes can bias their abundance. In this study, two tests are proposed to assess transport by the dynamical core of an AGCM. To separate transport from chemistry, the tests focus on the age-of-air, an estimate of the mean transport time by the circulation. The tests assess the coupled stratosphere-troposphere system, focusing on transport by the overturning circulation and isentropic mixing in the stratosphere, or Brewer-Dobson Circulation, where transport time-scales on the order of months to years provide a challenging test of model numerics. Four dynamical cores employing different numerical schemes (finite-volume, pseudo-spectral, and spectral-element) and discretizations (cubed sphere versus latitude-longitude) are compared across a range of resolutions. The subtle momentum balance of the tropical stratosphere is sensitive to model numerics, and the first intercomparison reveals stark differences in tropical stratospheric winds, particularly at high vertical resolution: some cores develop westerly jets and others easterly jets. This leads to substantial spread in transport, biasing the age-of-air by up to 25% relative to its climatological mean, making it difficult to assess the impact of the numerical representation of transport processes. This uncertainty is removed by constraining the tropical winds in the second intercomparison test, in a manner akin to specifying the Quasi-Biennial Oscillation in an AGCM. The dynamical cores exhibit qualitative agreement on the structure of atmospheric transport in the second test, with evidence of convergence as the horizontal and vertical resolution is increased in a given model. Significant quantitative differences remain, however, particularly between models employing spectral versus finite-volume numerics, even in state-of-the-art cores.