Impacts of aerosol-radiation interaction on meteorological forecasts over northern China by offline coupling of the WRF-Chem-simulated aerosol optical depth into WRF: a case study during a heavy pollution event

To facilitate the future inclusion of aerosol-radiation interactions in the regional operational numerical weather prediction (NWP) system RMAPS-ST (adapted from Weather Research and Forecasting, WRF) at the Institute of Urban Meteorology (IUM), China Meteorological Administration (CMA), the impacts of aerosol-radiation interactions on the forecast of surface radiation and meteorological parameters during a heavy pollution event (6-10 December 2015) over northern China were investigated. The aerosol information was simulated by RMAPSChem (adapted from the WRF model coupled with Chemistry, WRF-Chem) and then offline-coupled into the Rapid Radiative Transfer Model for General Circulation Models (RRTMG) radiation scheme of WRF to enable the aerosol-radiation feedback in the forecast. To ensure the accuracy of the high-frequency (hourly) updated aerosol optical depth (AOD) field, the temporal and spatial variations of simulated AOD and aerosol extinction coefficient at 550 nm were evaluated against in situ and satellite observations. Comparisons with in situ and Moderate Resolution Imaging Spectroradiometer (MODIS), AErosol Robotic NETwork (AERONET), and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) satellite observations showed that the model could reproduce the spatial and vertical distribution as well as the temporal variation of the polluted episode. Further comparison of PM2.5 with in situ observation showed WRF-Chem reasonably captured the PM2.5 field in terms of spatial distribution and magnitude, with the correlation coefficients of 0.85, 0.89, 0.76, 0.92 and 0.77 in Beijing, Shijiazhuang, Tianjin, Hebei and Henan, respectively. Forecasts with and without the aerosol information were conducted further, and the differences of surface radiation, energy budget and meteorological parameters were evaluated against surface and sounding observations. The offline-coupling simulation (with aerosol-radiation interaction active) showed a remarkable decrease in downward shortwave (SW) radiation reaching the surface, thus helping to reduce the overestimated SW radiation during the daytime. The simulated surface radiation budget was also improved, with the biases of net surface radiation decreased by 85.3 %, 50.0 %, 35.4 % and 44.1 % during the daytime in Beijing, Tianjin, Taiyuan and Jinan respectively, accompanied by the reduction of sensible (16.1 W m(-2), 18.5 %) and latent (6.8 W m(-2), 13.4 %) heat fluxes emitted by the surface around noon. In addition, the cooling of 2 m temperature (similar to 0.40 degrees C) and the decrease in horizontal wind speed near the surface (similar to 0.08 m s(-1)) caused by the aerosol-radiation interaction over northern China helped to reduce the bias by similar to 73.9 % and similar to 7.8 % respectively, particularly during the daytime. Further comparisons indicated that the simulation-implemented AOD could better capture the vertical structure of atmospheric wind. Accompanied with the lower planetary boundary layer and the increased atmospheric stability, both U and V wind at 850 hPa showed convergences which were unfavorable for pollutant dispersion. Since RMPAS-ST provides meteorological initial conditions for RMAPS-Chem, the changes of meteorology introduced by aerosol-radiation interaction would routinely impact the simulations of pollutants. To verify the statistical significance of the results, we further conducted the 24 h forecasts for a longer period lasting 27 d (13 January-8 February 2017), with no AOD field (NoAero) and WRF-Chem-simulated hourly AOD fields (Aero) included, as well as a constant AOD value of 0.12 (ClimAero). The 1-month results were statistically significant and indicated that the mean RMSE of 2 m temperature (wind speed at 10 m) in Aero and ClimAero relative to NoAero was reduced by 4.0 % (1.9 %) and 1.2 % (1.6 %). More detailed evaluations and analysis will be addressed in a future article. These results demonstrated the influence of aerosol-radiation interactions on the improvement of predictive accuracy and the potential prospects to offline coupling of near-real-time aerosol information in regional RMAPS-ST NWP in northern China.