By utilizing top-of-atmosphere radiation (TOAR) data from China’s new generation of geostationary satellites (FY-4A and FY-4B) along with interpretable machine learning models, near-surface particulate matter concentrations in China were estimated, achieving hourly temporal resolution, 4 km spatial resolution, and 100% spatial coverage. First, the cloudless TOAR data were matched and modeled with the solar radiation products from the ERA5 dataset to construct and estimate a fully covered TOAR dataset under assumed clear-sky conditions, which increased coverage from 20–30% to 100%. Subsequently, this dataset was applied to estimate particulate matter. The analysis demonstrated that the fully covered TOAR dataset (R² = 0.83) performed better than the original cloudless dataset (R² = 0.76). Additionally, using feature importance scores and SHAP values, the impact of meteorological factors and air mass trajectories on the increase in PM₁₀ and PM_2.5 during dust events were investigated. The analysis of haze events indicated that the main meteorological factors driving changes in particulate matter included air pressure, temperature, and boundary layer height. The particulate matter concentration products obtained using fully covered TOAR data exhibit high coverage and high spatiotemporal resolution. Combined with data-driven interpretable machine learning, they can effectively reveal the influencing factors of particulate matter in China.

Precise cloud and aerosol identification hold paramount importance for a thorough comprehension of atmospheric processes, enhancement of meteorological forecasts, and mitigation of climate change. This study devised an automatic denoising cloud–aerosol classification deep learning algorithm, successfully achieving cloud–aerosol identification in atmospheric vertical profiles utilizing CALIPSO L1 data. The algorithm primarily consists of two components: denoising and classification. The denoising task integrates an automatic denoising module that comprehensively assesses various methods, such as Gaussian filtering and bilateral filtering, automatically selecting the optimal denoising approach. The results indicated that bilateral filtering is more suitable for CALIPSO L1 data, yielding SNR, RMSE, and SSIM values of 4.229, 0.031, and 0.995, respectively. The classification task involves constructing the U-Net model, incorporating self-attention mechanisms, residual connections, and pyramid-pooling modules to enhance the model’s expressiveness and applicability. In comparison with various machine learning models, the U-Net model exhibited the best performance, with an accuracy of 0.95. Moreover, it demonstrated outstanding generalization capabilities, evaluated using the harmonic mean F1 value, which accounts for both precision and recall. It achieved F1 values of 0.90 and 0.97 for cloud and aerosol samples from the lidar profiles during the spring of 2019. The study endeavored to predict low-quality data in CALIPSO VFM using the U-Net model, revealing significant differences with a consistency of 0.23 for clouds and 0.28 for aerosols. Utilizing U-Net confidence and a 532 nm attenuated backscatter coefficient to validate medium- and low-quality predictions in two cases from 8 February 2019, the U-Net model was found to align more closely with the CALIPSO observational data and exhibited high confidence. Statistical comparisons of the predicted geographical distribution revealed specific patterns and regional characteristics in the distribution of clouds and aerosols, showcasing the U-Net model’s proficiency in identifying aerosols within cloud layers.