We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Integration of PMF and explainable machine learning for source apportionment and ecological risk of microplastics in urban greenspaces
Summary
Researchers applied positive matrix factorisation (PMF) and explainable machine learning to investigate microplastic distribution, source apportionment, and ecological risk in urban greenspaces, finding abundances of 141-1,258 items/kg dominated by polypropylene (32.6%), polyethylene (27.9%), and PET (12.0%) fragments smaller than 100 µm. Agricultural activities (29.6%), mixed domestic-industrial emissions (24.1%), and traffic-related sources (23.5%) were the primary contributors, with ecological risk projected to reach moderate levels by 2030.
Microplastics (MPs) have emerged as a global environmental concern due to their widespread distribution and potential ecological risks. Urban greenspaces play a vital role in improving the quality of life for urban residents, and are threatened by MPs pollution. While previous studies on MPs have predominantly focused on agriculture soils, MPs pollution in urban greenspaces remains insufficiently explored. To address this gap, this study investigated the spatial distribution, source apportionment, and both current and future ecological risks of MPs pollution in urban greenspaces. The results showed that MPs abundance ranged from 141 to 1258 items/kg. Nearly half of MPs were predominantly fragments (54.3 %), and were smaller than 100 μm (49.2 %). The major types were polypropylene (32.6 %), polyethylene (27.9 %), and polyethylene terephthalate (12.0 %). Source apportionment indicated that MPs primarily originated from agriculture activities (29.6 %), mixed domestic-industrial emissions (24.1 %), and traffic-related sources (23.5 %). Although the current ecological risk of MPs to urban greenspaces was generally low, economic growth and transportation development are projected to drive future risk to reach moderate level by 2030. This study comprehensively identified the sources and ecological risks of MPs in urban greenspaces, providing valuable insights for developing targeted MPs pollution management strategies in urban systems.
Sign in to start a discussion.
More Papers Like This
Decoding the PlasticPatch: Exploring the Global MicroplasticDistribution in the Surface Layers of Marine Regions with InterpretableMachine Learning
Researchers applied four interpretable machine learning algorithms to a calibrated global marine microplastic dataset to construct a predictive model of surface-layer microplastic distribution, finding that biogeochemical and anthropogenic factors are the dominant drivers of global marine microplastic pollution patterns.
Decoding the Plastic Patch: Exploring the Global Microplastic Distribution in the Surface Layers of Marine Regions with Interpretable Machine Learning
Researchers used interpretable machine learning algorithms to predict global marine microplastic distribution patterns based on calibrated field data. The study found that biogeochemical and human activity factors had the greatest influence on microplastic concentrations, which ranged from about 0.2 to 27 particles per cubic meter across the world's oceans, providing a framework for pollution management and decision-making.
Source tracking, pollution load, and risk assessment of microplastics pollution in agricultural soils of Bangladesh using machine learning and multi-matrix approaches
One of the first comprehensive assessments of microplastic contamination in agricultural soils of Bangladesh found widespread MP occurrence across 64 samples from eight areas, with ecological risk assessment indicating potential harm to soil organisms. The study linked MP sources to irrigation water, plastic mulch, and sewage sludge application.
What Drives Microplastic Exposure in Human Blood and Feces? Machine Learning Reveals Potential Key Influencing Factors
Researchers analyzed 229 blood and 227 fecal samples for microplastics using pyrolysis-GC-MS and applied machine learning to identify the strongest predictors of microplastic body burden. The model identified diet, packaging use, and indoor environment as key drivers of microplastic levels in human blood and feces, highlighting lifestyle factors as modifiable exposure determinants.
Parks and Recreational Areas as Sinks of Plastic Debris in Urban Sites: The Case of Light-Density Microplastics in the City of Amsterdam, The Netherlands
Researchers found that parks and recreational areas in Amsterdam act as significant sinks for light-density microplastics, with artificial turf infill, tire rubber, and film fragments as dominant types, suggesting urban green spaces accumulate substantial plastic pollution from recreational and maintenance activities.