Abstract Atmospheric aerosols originating from natural and anthropogenic sources have important implications for modeling atmospheric phenomena, but aerosol conditions can change significantly and rapidly because of their dependence on local geography and atmospheric conditions. In this work, we applied a computational k-means clustering algorithm to a global set of data obtained from the Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2), to yield a set of 25 clusters that discriminate on the basis of land type, elevation, and atmospheric conditions to predict statistical aerosol optical depth (AOD) information. We considered different subsets of MERRA-2 data, consisting of all the data averaged over a single year (2016) as well as data averaged by meteorological season over a span of five years (2012–16), arriving at five separate sets of 25 clusters. We make the clustered AOD information available with decision trees, qualitative cluster descriptions, and color-coded cluster maps to assist in identifying which cluster to use in retrieving AOD information. The results of this analysis have applications in atmospheric modeling where knowledge of approximate or typical aerosol conditions is needed in lookup-table form without requiring access to large atmospheric databases or computationally intensive aerosol models; such applications could include quick-turnaround or large-volume analyses of atmospheric conditions required to inform decision-making that affects national security, such as in modeling remote sensing and estimating upper and lower bounds for visible and infrared photon transport.