We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Evaluation of microplastic pollution in urban lentic ecosystem using remote sensing, GIS, and Support Vector Machine (SVM): relevance for environmental and ecological risk
Summary
Researchers assessed microplastic pollution in 24 urban ponds and lakes in Kolkata, India, finding significantly higher concentrations during the post-monsoon season, with fibers making up about 59% of all particles. They developed machine learning and remote sensing models that achieved up to 98% accuracy in identifying water bodies and predicting microplastic levels from satellite imagery. The study demonstrates that combining field sampling with remote sensing technology can enable large-scale monitoring of urban microplastic pollution.
Plastic waste is a major source of microplastic (MP) pollution, posing adverse environmental and public health risks. This study assessed MP abundance in 24 urban ponds and lakes within the Kolkata Municipal Corporation, India, during the post- and pre-monsoon seasons of 2022-2023. Results showed that MP concentrations were significantly higher in the post-monsoon season (20 ± 3.46 items L⁻; ANOVA, p < 0.05), with red, white, and black particles being the most prevalent. MPs prevalently ranged between 500 and 1000 µm with fibers constituting 58-59% of the total MPs. Fourier-transform infrared (FTIR) analysis identified polyethylene (PE) as the dominant polymer. MP abundance showed negative correlations with dissolved oxygen and turbidity, and positive associations with pH, TDS, BOD₅, and total coliform counts. A Support Vector Machine (SVM) model was developed for morphology-based MP classification, achieving an accuracy of 89%. Additionally, remote sensing and GIS techniques were used to develop index-based models for water-body identification and MP quantification (items L⁻) using spectral data from Sentinel-2 imagery. These models demonstrated high validation accuracy of 98.01% and 92.60%, respectively. Metal analysis of sediment and MPs of water detected chromium, suggesting possible MP-metal interactions within sediments. Although the Pollution Load Index (PLI) indicated relatively low contamination levels, the Polymer Hazard Index (PHI) exceeded 1000, indicating substantial ecological risk. Future studies should focus on long-term monitoring, socio-economic and health impact assessments and development of effective mitigation strategies particularly addressing plastic-waste derived-MPS.