Joint Retrieval of PM_2.5 Concentration and Aerosol Optical Depth over China Using Multi-Task Learning on FY-4A AGRI

Aerosol optical depth (AOD) and fine particulate matter with a diameter of less than or equal to 2.5 μm (PM_2.5) play crucial roles in air quality, human health, and climate change. However, the complex correlation of AOD–PM_2.5 and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location. On this point, a multi-task learning (MTL) model, which enables the joint retrieval of PM_2.5 concentration and AOD, is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager (FY-4A AGRI), and compared to that of two single-task learning models—namely, Random Forest (RF) and Deep Neural Network (DNN). Specifically, MTL achieves a coefficient of determination (R²) of 0.88 and a root-mean-square error (RMSE) of 0.10 in AOD retrieval. In comparison to RF, the R² increases by 0.04, the RMSE decreases by 0.02, and the percentage of retrieval results falling within the expected error range (Within-EE) rises by 5.55%. The R² and RMSE of PM_2.5 retrieval by MTL are 0.84 and 13.76 μg m⁻³, respectively. Compared with RF, the R² increases by 0.06, the RMSE decreases by 4.55 μg m⁻³, and the Within-EE increases by 7.28%. Additionally, compared to DNN, MTL shows an increase of 0.01 in R² and a decrease of 0.02 in RMSE in AOD retrieval, with a corresponding increase of 2.89% in Within-EE. For PM_2.5 retrieval, MTL exhibits an increase of 0.05 in R², a decrease of 1.76 μg m⁻³ in RMSE, and an increase of 6.83% in Within-EE. The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM_2.5 retrievals, demonstrating a significant advantage in efficiently capturing the spatial distribution of PM_2.5 concentration and AOD.