•  
  •  
 

A USER-FRIENDLY AI-DRIVEN SIMULATION MODEL TO ESTIMATE AND REDUCE DAILY MICROPLASTIC EXPOSURE

Abstract

Microplastic pollution is an escalating global concern, with growing evidence of its widespread presence in food, air, and water. Despite extensive research quantifying microplastic contamination across various environments, translating these findings into practical tools for public awareness and individual health risk assessment remains a significant challenge. This study introduces a user-friendly simulation model designed to estimate daily microplastic exposure by integrating diverse data sources and human activity patterns. The model incorporates key factors, including airborne microplastic concentrations, dietary microplastic levels, human inhalation rates, and domestic dietary habits. Leveraging advanced AI techniques such as data harmonization, feature selection, and symbolic regression, the model synthesizes these inputs into an intuitive predictive equation. This equation allows individuals to estimate their microplastic exposure by inputting macro-environmental data (e.g., geographic factor) and personalized lifestyle data, such as dietary preferences and time spent indoors versus outdoors. This study bridges the gap between scientific knowledge and public understanding by offering an accessible tool to quantify personal microplastic exposure. By providing actionable insights, the model not only enhances public awareness but also empowers users to make informed decisions to reduce exposure risks in their daily lives. This work highlights the importance of continued interdisciplinary collaboration to translate environmental research into practical solutions that benefit society.

This document is currently not available here.

Share

COinS