Author(s)

Qi Chen

Corresponding Author

Qi Chen

Abstract

Microplastics are a persistent and widespread pollution existing in the environment. Despite recognizing the harmful effects of MPs on human health and the ecosystem, researchers have suggested that MPs can serve as vectors in spreading pathogens. This highlights the urgency of developing a machine learning model to assess the associative risks. After analysing the global wastewater treatment plant distribution and the corresponding waste discharged, we identified that Bohai Sea deserves significant attention due to its high level of pollution and potential risks for pathogen transmission via microplastics. As a result, in this study, we developed an Artificial Neural Network model to predict the relative abundance of Vibrio spp. on the surface of microplastics in the Bohai Sea, China. Specifically, 483 data points were utilized to train the model, which incorporates environmental parameters such as temperature, salinity, dissolved oxygen, pH, total nitrogen, and total phosphorus. With a determination coefficient (R²) of 0.87 and a mean absolute error (MAE) of 5.8, our model indicates a moderate level of accuracy, with improved performance in predicting middle-ranged data compared to extreme data. In the future, we can use more comprehensive datasets to explore the role of microplastics in transmitting other pathogens and toxic substances, which will provide insights into preventing disease infections and reducing marine pollution.

Keywords

Microplastics; Machine learning; Artificial Neural Network; Vibrio spp.