What question did this study set out to answer?

The study aims to enhance the retrieval of aerosol properties, addressing limitations of existing methods that use static observations.

March 28, 2026Open Access

Advanced Time series Multi-wavelength AOD Transformer (TMAT) model: joint retrieval of aerosol optical and microphysical properties using Himawari-8 AHI data

Puntos clave

The study aims to enhance the retrieval of aerosol properties, addressing limitations of existing methods that use static observations.
Developed a Time series Multi-wavelength AOD Transformer (TMAT) model.
Used two years of Himawari-8 full-disk data matched with AERONET/SONET observations.
Applied end-to-end learning with a Transformer architecture to utilize temporal information.
Conducted site-based 5-fold cross-validation for performance evaluation.
Achieved RMSE values of 0.095, 0.039, and 0.042 for fAOD, cAOD, and SSA respectively.
Correlation coefficients for AOD at 550 nm were 0.952, 0.955, and 0.762.
60% to 81.80% of retrievals met Global Climate Observing System requirements.
TMAT's attention weights correlated well with atmospheric path lengths and scattering angles.

Resumen

• Proposes an advanced Time series Multi-wavelength AOD Transformer (TMAT) for fAOD, cAOD the root mean square errors (RMSEs) were 0.092, 0.095 and 0.039; and 60.02%, 61.54% and 81.80% of the retrievals met Global Climate Observing System requirements. SSA and absorption AOD retrievals at 440 nm exhibited RMSE (R) values of 0.042 (0.552) and 0.037 (0.736), respectively. For AOD (550 nm) ≥ 0.3, the R values for the derived Ångström Exponent and fine mode fraction were 0.786 and 0.817, with corresponding RMSEs of 0.199 and 0.093. TMAT’s Transformer attention weights exhibited physically consistent behavior by assigning greater weights to observations with longer atmospheric path lengths and smaller scattering angles, where such geometric conditions enhanced aerosol signal sensitivity. These results pave the way for generating multiple aerosol product using Himawari-8/9 satellite data under the TMAT framework.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo