TY  - Data
T1  - Physical and Deep Learning Retrieval of Aerosol Fine Mode Proportions (Phy-DL FMF) (2001-2020)
A1  - Yan Xing
DO  - 10.5281/zenodo.5105617
PY  - 2024
DA  - 2024-05-21
PB  - National Cryosphere Desert Data Center
AB  - The fine mode ratio (FMF) is crucial for distinguishing between natural aerosols and anthropogenic aerosols. However, currently most satellite based land aerosol fine model fraction products are highly unreliable. Here, we have developed a new satellite based global land daily FMF dataset (Phy DL FMF) that covers the period from 2001 to 2020 at a spatial resolution of 1°, leveraging the advantages of collaborative physics and deep learning methods. Based on the analysis of 361089 data samples from 1170 AERONET sites worldwide, the Phy DL FMF dataset is comparable to the measurement results of the Aerosol Robot Network (AERONET). Overall, the root mean square error (RMSE) of Phy DL FMF is 0.136, the correlation coefficient is 0.68, and the proportion of results within the expected error (EE) range of ± 20% is 79.15%. In addition, off-site validation of the Surface Radiation Budget (SURFRED) observation results showed that the root mean square error of Phy DL FMF was 0.144 (72.50% of the results were within ± 20% of the expected error (EE) range). The performance of Phy DL FMF is superior to other deep learning or physical methods (such as the spectral deconvolution algorithm proposed in our previous research), especially in forest, grassland, cultivated land, as well as urban and barren land types. As a long-term dataset, Phy DL FMF is able to show a significant downward trend in the overall terrestrial regions worldwide (with a significance level of 95%). According to the trend analysis of Phy DL FMF in different countries, the upward trend of FMF is particularly evident in India and the western United States. In summary, this study provides a new aerosol full factor dataset for global land regions, which helps to enhance our understanding of the spatiotemporal variations of fine and coarse aerosol patterns.
DB  - NCDC
UR  - http://www.ncdc.ac.cn/portal/metadata/cf259861-b46d-4fed-aad8-a0d293cd04dd
ER  -