A common challenge of Atmospheric measurements in remote environments is to identify local pollution from nearby sources. During the MOSAiC (Multidisciplinary drifting Observatory for the Study of Arctic Climate) expedition, we measured aerosol and gaseous atmospheric composition on the bow of the research vessel Polarstern in the Arctic Ocean. Our measurements were occasionally impacted by pollution from the ship exhaust, or by ongoing activities on sea-ice such as passing skidoos or use of generators. We developed an automated method to identify such pollution events. Here, we present the algorithm used to clean the aerosol dataset collected during the MOSAiC expedition.