0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Environmental Sources Marine & Wildlife Policy & Risk Remediation Sign in to save

AI-Enabled Plastic Pollution Monitoring System for Toronto Waterways

2023 2 citations ? Citation count from OpenAlex, updated daily. May differ slightly from the publisher's own count.
Benjamin Kelly, Shengkai Chen, Eric Pengyu Zhou, Maher Elshakankiri

Summary

Researchers developed an AI-based monitoring system to detect plastic pollution in Toronto waterways using camera sensors. Automated AI monitoring enables continuous, large-scale tracking of plastic pollution, which is the precursor to the microplastics that accumulate in aquatic ecosystems.

Study Type Environmental

Plastic pollution in waterways is a severe environmental concern predicted to increase globally in the coming years. Many activists and research groups are currently invested in monitoring pollution and removing plastics from aquatic ecosystems. However, with much focus on microplastics and the direct removal of larger plastics, accurate data on the sources and pathways of larger floating plastics in freshwater environments is scarce. We present an IoT system with an integrated computer vision model to identify and store data on trash in natural settings. This would include a camera sensor system, edge computing, cloud storage, and the eventual implementation of connected trash-collecting robots. Such a system deployed at multiple sites would inform trash monitoring and removal efforts while providing invaluable open-access environmental data for researchers and future technologies.

Share this paper