A Two-Stage Machine Learning Algorithm for Retrieving Multiple Aerosol Properties Over Land: Development and Validation

Satellite-based aerosol optical property retrieval over land, especially size-related parameters, is challenging. This study proposed a novel two-stage machine learning (ML) algorithm for retrieving aerosol optical depth (AOD), angstrom ngstrom exponent (AE), fine mode fraction (FMF), and fine mode AOD (FAOD) over land using Moderate Resolution Imaging Spectroradiometer (MODIS) observed reflectance. The new ML algorithm consists of three steps: 1) all samples extracted from Aerosol Robotic Network (AERONET) measurements were used to train the ML model; 2) then, to reduce the extreme estimation bias of the model, divided low- and high-value samples were used to train low- and high-value ML models, respectively; and 3) finally, the three ML models were integrated into the final retrieval based on the weight interpolation. Independent site network validation results show that the new ML algorithm has a Pearson correlation coefficient (R) of 0.894 (0.638, 0.661, and 0.865) and the root mean square error (RMSE) of 0.146 (0.258, 0.245, and 0.153) for the AOD (AE, FMF, and FAOD) retrieval, which significantly outperforms the validation metrics of MODIS operational products, with AOD (AE, FMF, and FAOD) RMSE of 0.130-0.156 (0.536-0.569, 0.313, and 0.191). The intercomparison of aerosol products shows that the spatial patterns of AOD, AE, FMF, and FAOD of the new ML algorithm are in good agreement with those of the MODIS, and Polarization and Directionality of Earth Reflectance (POLDER) products. These results illustrate that the new ML algorithm has good performance and transferability, and indicate the ability of ML methods to be applied to multispectral instruments (such as MODIS) to retrieve multiple aerosol properties.