Fig 1.
Spatial extent of the study area. The left panel shows the national outline of Ghana, which serves as the primary spatial domain for the AOD analysis.
The top-right panel highlights the Western Region, with a focus on Takoradi, a coastal urban area where high aerosol levels were observed. The bottom panel zooms into the Greater Accra Region, encompassing Accra, another major metropolitan area with elevated AOD values. These regions were selected for both national-scale and regional-scale AOD modeling using MODIS AOD data at approximately 10 km spatial resolution. Base map shapefile from OCHA via humanitarian data exchange (https://data.humdata.org/dataset/cod-ab-gha), licensed under CC BY 4.0.
Table 1.
Summary of datasets used in the study. The “Count” column reflects the number of valid monthly observations retained for modeling after applying all quality control, filtering, and temporal alignment procedures.
Table 2.
Performance metrics for selected hyperparameter configurations of AOD satellite datasets (AQUA and TERRA) across the study region.
Table 3.
Best hyperparameters from Keras tuner.
Fig 2.
Average AOD distribution over Ghana from aqua retrievals spanning 2003–2019.
Base map shapefile from OCHA via humanitarian data exchange (https://data.humdata.org/dataset/cod-ab-gha), licensed under CC BY 4.0.
Fig 3.
Average AOD distribution over Ghana from Terra retrievals spanning 2003–2019.
Base map shapefile from OCHA via humanitarian data exchange (https://data.humdata.org/dataset/cod-ab-gha), licensed under CC BY 4.0.
Fig 4.
Relative feature importance of meteorological and surface variables for predicting Aerosol Optical Depth (AOD) in Ghana, based on Random Forest models trained on (a) TERRA and (b) AQUA datasets.
Variables include shortwave radiation (shortwave), latent heat flux (latent), sensible heat flux (sensible), evaporation rate (evaporation), surface temperature (temp), surface pressure (pressure), precipitation (precip), low cloud cover (lcc), solar radiation (solar_radiation), boundary layer height (blh), dew point temperature (dewpoint), surface longwave radiation (longwave), relative humidity (RH), and ultraviolet radiation (uv_radiation). Results highlight that shortwave radiation and flux-based variables dominate AOD prediction, with notable differences in feature ranking between morning (TERRA) and afternoon (AQUA) satellite overpasses.
Fig 5.
Annual and monthly AOD trends from AQUA and TERRA datasets over Ghana (2003–2019).
Top left panel: annual mean AOD. Top right panel: monthly climatology Bottom: number of high AOD days (AOD>0.509 (national average)).
Fig 6.
Correlation matrix between AOD products (AOD AQUA and AOD TERRA) and selected meteorological and surface variables.
Variables include boundary layer height (blh), sensible heat flux (sensible), latent heat flux (latent), surface temperature (temp), low cloud cover (lcc), net shortwave radiation (shortwave), dew point temperature (dewpoint), surface longwave radiation (longwave), relative humidity (RH), evaporation, surface pressure (pressure), total solar radiation (solar radiation), ultraviolet radiation (uv radiation), and precipitation (precip). Positive correlations are shown in red and negative correlations in blue. Strong correlations (absolute r>0.6) highlight key variables potentially influencing AOD behavior across different times of day and surface conditions.
Fig 7.
Error metrics for the predicted spatial distribution of AOD levels from Terra retrievals over Ghana spanning 2003–2019.
Base map shapefile from OCHA via humanitarian data exchange (https://data.humdata.org/dataset/cod-ab-gha), licensed under CC BY 4.0.
Fig 8.
Error metrics for the predicted spatial distribution of AOD levels from Aqua retrievals over Ghana spanning 2003–2019.
Base map shapefile from OCHA via humanitarian data exchange (https://data.humdata.org/dataset/cod-ab-gha), licensed under CC BY 4.0.
Fig 9.
Comparison between AOD distributions: urban cities vs national.
Fig 10.
Comparison between predicted and observed variations in AOD levels over selected locales.
Table 4.
Summary of the various metrics employed over selected locales.