Convolutions, clusters, and characterizations: Using pretrained networks for back trajectory analysis

Image analysis is integral in understanding the increasing abundance of atmospheric science imagerydata. Whereas time-consuming analysis of individual images or simplified image processing techniqueswere previously necessary, machine learning can now quickly learn trends in and distinctions betweenimages. However, training deep learning models on large datasets can be computationally expensive.Leveraging the architectures and weights of pre-trained neural networks can alleviate some expense. Inthis work, we apply pre-trained networks to back trajectory images generated for the NASA AerosolCloud meTeorology Interactions oVer the western north ATlantic Experiment (ACTIVATE) campaign.We find this method outperforms the principal component analysis baseline and results in fourgeographically distinct clusters. Pairing these images with the host of measurements taken during theACTIVATE campaign, we find the regions to also be distinct in their bulk characteristics of chemical andmicrophysical variables.