An aerosol classification scheme for global simulations using the K-means machine learning method

A machine learning K-means algorithm is applied to data of seven aerosol properties from a global aerosol simulation using EMAC-MADE3. The aim is to partition the aerosol properties across the global atmosphere in specific aerosol regimes. K-means is an unsupervised machine learning method with the advantage that an a priori definition of the aerosol classes is not required. Using K-means, we are able to quantitatively define global aerosol regimes, so-called aerosol clusters, and explain their internal properties as well as their location and extension. This analysis shows that aerosol regimes in the lower troposphere are strongly influenced by emissions. Key drivers of the clusters’ internal properties and spatial distribution are, for instance, pollutants from biomass burning/biogenic sources, mineral dust, anthropogenic pollution, as well as their mixing. Several continental clusters propagate into oceanic regions. The identified oceanic regimes show a higher degree of pollution in the northern hemisphere than over the southern oceans. With increasing altitude, the aerosol regimes propagate from emission-induced clusters in the lower troposphere to roughly zonally distributed regimes in the middle troposphere and in the tropopause region. Notably, three polluted clusters identified over Africa, India and eastern China, cover the whole atmospheric column from the lower troposphere to the tropopause region. A markedly wide application potential of the classification procedure is identified and further aerosol studies are proposed which could benefit from this classification.