摘要：One of the challenges in studying desert dust aerosol along with its numerous interactions and impacts is the paucity of direct in situ measurements, particularly in the areas most affected by dust storms. Satellites typically provide column-integrated aerosol measurements, but observationally constrained continuous 3D dust fields are needed to assess dust variability, climate effects and impacts upon a variety of socio-economic sectors. Here, we present a high-resolution regional reanalysis data set of desert dust aerosols that covers Northern Africa, the Middle East and Europe along with the Mediterranean Sea and parts of central Asia and the Atlantic and Indian oceans between 2007 and 2016. The horizontal resolution is 0.1∘ latitude × 0.1∘ longitude in a rotated grid, and the temporal resolution is 3 h. The reanalysis was produced using local ensemble transform Kalman filter (LETKF) data assimilation in the Multiscale Online Nonhydrostatic AtmospheRe CHemistry model (MONARCH) developed at the Barcelona Supercomputing Center (BSC). The assimilated data are coarse-mode dust optical depth retrieved from the Moderate Resolution Imaging Spectroradiometer (MODIS) Deep Blue Level 2 products. The reanalysis data set consists of upper-air variables (dust mass concentrations and the extinction coefficient), surface variables (dust deposition and solar irradiance fields among them) and total column variables (e.g. dust optical depth and load). Some dust variables, such as concentrations and wet and dry deposition, are expressed for a binned size distribution that ranges from 0.2 to 20 µm in particle diameter. Both analysis and first-guess (analysis-initialized simulation) fields are available for the variables that are diagnosed from the state vector. A set of ensemble statistics is archived for each output variable, namely the ensemble mean, standard deviation, maximum and median. The spatial and temporal distribution of the dust fields follows well-known dust cycle features controlled by seasonal changes in meteorology and vegetation cover. The analysis is statistically closer to the assimilated retrievals than the first guess, which proves the consistency of the data assimilation method. Independent evaluation using Aerosol Robotic Network (AERONET) dust-filtered optical depth retrievals indicates that the reanalysis data set is highly accurate (mean bias = −0.05, RMSE = 0.12 and r = 0.81 when compared to retrievals from the spectral de-convolution algorithm on a 3-hourly basis). Verification statistics are broadly homogeneous in space and time with regional differences that can be partly attributed to model limitations (e.g. poor representation of small-scale emission processes), the presence of aerosols other than dust in the observations used in the evaluation and differences in the number of observations among seasons. Such a reliable high-resolution historical record of atmospheric desert dust will allow a better quantification of dust impacts upon key sectors of society and economy, including health, solar energy production and transportation. The reanalysis data set (Di Tomaso et al., 2021) is distributed via Thematic Real-time Environmental Distributed Data Services (THREDDS) at BSC and is freely available at http://hdl.handle.net/21.12146/c6d4a608-5de3-47f6-a004-67cb1d498d98 (last access: 10 June 2022).
