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.
Sign in to start a discussion.
More Papers Like This
AI-Driven Framework Development for Predictive Classification of Microplastic Concentration of Aquatic Systems in the United States
Researchers compared four machine learning models—logistic regression, random forest, support vector machine, and a neural network—for predicting microplastic density in US coastal waters across three regions. The support vector machine performed best with 93.94% average accuracy, demonstrating the potential of AI-driven tools for microplastic monitoring.
[Overview of the Application of Machine Learning for Identification and Environmental Risk Assessment of Microplastics].
This review examines the application of machine learning (ML) methods for identifying microplastics and assessing their environmental risks, covering techniques for improving the accuracy and reliability of microplastic detection across different environmental media. Researchers highlight how ML can systematically analyse pollution characteristics and support ecological risk evaluation of microplastic contamination.
Predicting microplastic quantities in Indonesian provincial rivers using machine learning models
This study used machine learning models to predict microplastic levels in rivers across 24 Indonesian provinces based on environmental and economic data. Temperature, economic output, and population density were the strongest predictors of microplastic pollution. The approach could help environmental agencies monitor and manage microplastic contamination in freshwater systems more efficiently.
Application of machine learning in assessing spatial distribution patterns of soil microplastics: a case study of the Bang Pakong Watershed, Thailand
Machine learning models were applied to predict spatial distribution patterns of microplastics in soils across a Thai watershed, identifying land use types and proximity to water bodies as key factors driving contamination levels.
Meta-Analysis of Satellite Observations for United Nations Sustainable Development Goals: Exploring the Potential of Machine Learning for Water Quality Monitoring
This meta-analysis and bibliometric review found that machine learning models, particularly random forest and neural networks, outperform conventional statistical methods for satellite-based water quality monitoring. While focused on remote sensing rather than microplastics directly, the methods could be applied to large-scale tracking of plastic pollution in surface waters.