Aerosol classification using fuzzy clustering over a tropical rural site

Abstract

Exact knowledge on the types of aerosols present over a region is very important in the radiative forcing estimates. Several techniques are available to classify aerosols, which have their own pros and cons. In the present study, a soft clustering technique, Fuzzy C-Means (FCM) is employed to classify aerosols using multiple aerosol parameters over a rural site Gadanki (13.48oN, 79.18°E), India. The optical and microphysical properties of the aerosols (26 parameters) derived from long-term measurements of the Sky Radiometer (from April 2008 to October 2020) are utilized for cluster analysis. The three resultant clusters were found to be distinct and compact based on high intra-cluster similarity and low inter-cluster similarity. By comparing the clustering results of different subsets of data and testing the robustness of the FCM algorithm, we found that the correct classification percentage for each scenario was about 98.4%. Even by introducing a 10% random error for each of the aerosol microphysical properties used in the cluster analysis, around 94.5% of the records were found to retain the original clusters. Based on the aerosol properties of the clusters, the three clusters were identified as mixed mode moderately absorbing, mixed mode slightly absorbing, and coarse mode slightly absorbing type of aerosols. While comparing with the global aerosol models, these three aerosol types showed similarities with biomass burning, polluted marine, and polluted continental aerosol types. Significant seasonal variability of the identified aerosol types was observed, with biomass burning type dominating in the pre-monsoon season, polluted marine during the monsoon season, and polluted continental in a relatively higher percentage compared to the other two types in winter and post-monsoon seasons. An increasing trend in polluted marine aerosol type is noticed, whilst biomass burning and polluted continental showed decreasing trends. Furthermore, the existing knowledge on various aspects of aerosols over Gadanki ascertains that the identified aerosol types are reasonable, implying that the FCM clustering technique for aerosol classification is effective and it might be extend to other locations.