The New Stand-Alone Surface Analysis at ECMWF: Implications for Land-Atmosphere DA Coupling

This article presents the "screen-level and surface analysis only" (SSA) system at the European Centre for Medium-Range Weather Forecasts (ECMWF). SSA is a simplification of the operational land-atmosphere weakly coupled data assimilation (WCDA). The goal of SSA is to provide 1) efficient research into land surface developments in NWP and 2) land reanalyses with land-atmosphere coupling. SSA maintains a coupled forecast model between assimilation cycles, but the atmospheric analysis is not performed; rather, it is forced from an archived analysis. Hence, SSA is much faster than WCDA, although it lacks feedback between the land and atmospheric analyses. A global sensitivity analysis was performed over one year to compare the WCDA and SSA systems. Prescribed proxy 2-m temperature/humidity screen-level observation errors were approximately doubled in the soil moisture data assimilation, thereby reducing the average size of the root-zone soil moisture analysis increments by about 60%. The systematic impact of these changes on the WCDA surface and near-surface atmospheric dynamics was effectively captured by SSA, although the short-term impact was underestimated. Importantly, the SSA forecast verification scores accurately reflected those of WCDA: atmospheric 1-10-day temperature/humidity forecasts were degraded in the tropics and lower midlatitudes up to about 700 hPa. The soil moisture analysis performance was not significantly impacted. These results endorse SSA as an NWP research tool and confirm the role of assimilating proxy screen-level observations in the soil moisture analysis to improve weather forecasts. Appropriate use and limitations of SSA are considered.