The health and environmental risks posed by microplastics in the atmosphere cannot be underestimated. These particles contaminate water sources, soil, and air, leading to their ingestion by wildlife and humans. This can cause physical harm to organisms and introduce toxic chemicals into the food chain. Furthermore, microplastics disrupt ecosystems, affect biodiversity, and contribute to the decline of marine and terrestrial species, posing serious long-term risks to both environmental and human health. To enhance the efficiency and accuracy of detecting atmospheric pollutants, this study introduces the combination of laser-induced breakdown spectroscopy (LIBS) technology and machine learning for the classification of microplastics in the atmosphere. Principal component analysis is employed to reduce the dimensionality of the data. Subsequently, a supervised machine learning algorithm based on backpropagation artificial neural networks (BP-ANNs) is applied to identify microplastics in the atmosphere. The high accuracy of BP-ANN demonstrates the feasibility of classifying atmospheric microplastics using LIBS technology. The study explores the impact of atmospheric humidity on microplastic content, contributing significantly to atmospheric environmental protection and biological health. Finally, data fusion is employed to further enhance the classification accuracy of microplastics in the atmosphere.