Analyzing Aerosol Effect on Deep Convective Clouds over the Global Oceans By Using AI Based Techniques

NOAA long-term (1982-2019) satellite climate data records (CDRs) of aerosol and cloud along with NCEP meteorological reanalysis are used to study the aerosol effects on deep convective clouds (DCCs) over the global oceans from a climatology perspective. Specifically, AI techniques, including SHAP (SHapley Additive exPlanations) analyzing tool and BPNN (Back-Propagation Neural Network) model, are used to identifying the correlation and mutual dependence of aerosol, cloud, and meteorological variables. The objective is to identify sensitive aerosol regimes and geolocations of the aerosol effects on DCCs. The limitations of our study and further improvement will be discussed too.