Full-coverage 250 m monthly aerosol optical depth dataset (2000–2019) amended with environmental covariates by an ensemble machine learning model over arid and semi-arid areas, NW China

Aerosols are a complex compound with a great effect on the global radiation balance and climate system even human health, and concurrently are a large uncertain source in the numerical simulation process. The arid and semi-arid area has a fragile ecosystem, with abundant dust, but lacks related aerosol data or data accuracy. To solve these problems, we use the bagging trees ensemble model, based on 1 km aerosol optical depth (AOD) data and multiple environmental covariates, to produce monthly advanced-performance, full-coverage, and high-resolution (250 m) AOD products (named FEC AOD, Fusing Environmental Covariates AOD) in the arid and semi-arid areas. Then, based on FEC AOD, we analyzed the spatiotemporal pattern of AOD and further discussed the interpretation of environmental covariates to AOD. The result shows that the bagging trees ensemble model has a good performance, with its verification R2 always keeping at 0.90 and the R2 being 0.79 for FEC AOD compared with AERONET. The high AOD areas are located in the Taklimakan Desert and the Loess Plateau, and the low AOD area is concentrated in the south of Qinghai province. The higher the AOD is, the stronger the interannual variability. Interestingly, the AOD indicates a dramatic decrease in Loess Plateau and an evident increase in the southeast Taklimakan Desert, while the AOD in the southern Qinghai province almost shows no significant change between 2000 and 2019. The annual variation characteristics present that AOD is the largest in spring (0.267) and the smallest in autumn (0.147); the AOD pattern in Gansu province is bimodal, but unimodal in other provinces. The farmland and construction land are at high AOD levels compared with other land cover types. The meteorological factors demonstrate a maximum interpretation of AOD on all set temporal scales, followed by the terrain factors, and the surface properties are the smallest, i.e., 77.1 %, 59.1 %, and 50.4 % respectively on average. The capability of the environmental covariates for explained AOD varies with season, with an sequence being winter (86.6 %) > autumn (80.8 %) > spring (79.9 %) > summer (72.5 %). In this research, we pathbreakingly provide high spatial resolution (250 m) and long time series (2000–2019) FEC AOD dataset in arid and semi-arid regions to support the atmosphere and related study in northwest China, with the full data available at https://doi.org/10.5281/zenodo.5727119 (Chen et al., 2021a).