Publications

Ding, Y; Ni, WJ; Dong, JX; Yang, J; Meng, SY; Li, SW (2025). Spatiotemporal Analysis and Anomalous Trends of Asia AOD (2001-2024): Insights from a Deep Learning Fusion Model and EOF Decomposition. REMOTE SENSING, 17(10), 1741.

Abstract
Long-term investigations of Aerosol Optical Depth (AOD) across Asia are crucial for understanding its regional impacts on the global climate system. However, satellite-derived AOD datasets frequently suffer from missing values due to factors such as cloud cover, algorithmic limitations, and various atmospheric conditions. To overcome these challenges, this study employs the deep learning model TabNet, incorporating Digital Elevation Model (DEM) data and ERA5 meteorological variables, to fuse MERRA-2 AOD with MODIS MAIAC AOD observations. The resulting integration yields a high-resolution, seamless daily AOD dataset for Asia spanning the period from 2001 to 2024. The fused dataset demonstrates significant improvements over the original MERRA-2 AOD, with an increase in the coefficient of determination (R2) by 0.1065 and a reduction in root mean square error (RMSE) by 0.0369. Spatio-temporal analysis, conducted using Empirical Orthogonal Function (EOF) decomposition, reveals that AOD concentrations across Asia are strongly influenced by anthropogenic factors, including industrial activities, transportation emissions, and biomass burning. The results indicate a generally increasing trend in AOD from 2001 to 2014, followed by a declining trend from 2015 to 2024. Notably, EOF results show a marked rise in AOD levels in Mongolia after 2020, likely attributable to an uptick in dust storm activity. This research offers valuable insights into the spatiotemporal trends of aerosols across Asia, underscoring the need for sustained air quality measures to mitigate pollution and protect public health.

DOI:
10.3390/rs17101741

ISSN:
2072-4292