We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Using machine learning to reveal drivers of soil microplastics and assess their stock: A national-scale study
AI summary Read the abstract
Using machine learning on data from 621 sites across China, researchers identified nine key factors driving microplastic distribution in soil, including population density, plastic production, and agricultural practices. The study estimated that Chinese topsoil contains a substantial stock of microplastics, with concentrations varying widely by region. This large-scale analysis helps predict where microplastic contamination is worst, which is important for understanding human exposure through food grown in contaminated soil.
The issue of microplastic (MP) contamination in soil is a significant concern. However, due to limited large-scale studies and stock assessments, our understanding of the drivers of their distribution and fate remains incomplete. To address this, we conducted a comprehensive study in China, collected MP data from 621 sites, and utilized machine learning techniques for analysis. Our findings revealed 9 key factors influencing the distribution of soil MPs, highlighting their nonlinear influence processes. Among these factors, atmospheric deposition emerged as the most dominant driver, while wind and precipitation could lead to the transformation of soil from a sink to a source of MPs. MP concentrations in Chinese soils vary from 1.4 to 4333.1 particles/kg, with human activities significantly affecting their distribution, resulting in higher concentrations in the east and lower concentrations in the west. The estimated MP stock in Chinese soils is 1.92 × 10 particles, equivalent to a mass of 2.11-8.64 million tonnes. This stock alone surpasses that found in global oceans, making global soil the largest reservoir of MPs. Overall, this study enhances our understanding of the environmental behavior of MPs and provides valuable data and theoretical support for the prevention, control, and management of this contamination.
More Papers Like This
From mapping to modelling: the evolving multidimensional microplastic risks in China's farmlands
AI summary Read the abstract
Researchers combined a national-scale soil survey with machine learning models to map and project microplastic risks across China's farmlands through 2050, finding that agricultural film use, population density, and GDP are key drivers, and that regional risk rankings will shift counter-intuitively depending on which socioeconomic development pathway is followed.
Identification of potentially contaminated areas of soil microplastic based on machine learning: A case study in Taihu Lake region, China
AI summary Read the abstract
Researchers applied machine learning models — including random forest and support vector regression — to predict the spatial distribution of soil microplastic pollution in China's Taihu Lake region, finding that soil texture, population density, and proximity to known plastic sources were the dominant drivers, with nearly half of urban soils showing serious contamination.
Land use shapes the fate of soil microplastics in China: Insights from machine learning
AI summary Read the abstract
A massive study analyzing nearly 1,500 soil samples across China found that farmland, especially orchards and fields covered with plastic sheeting (mulch), had far more tiny plastic particles than forests or natural areas, with mulched fields showing about 6 times more contamination. Since these are the soils growing our food, this matters because it suggests the crops we eat may be absorbing more microplastics from heavily farmed, plastic-mulched land, highlighting a need for smarter farming practices to reduce this exposure.
Spatial Distributions, Compositional Profiles, Potential Sources, and Intfluencing Factors of Microplastics in Soils from Different Agricultural Farmlands in China: A National Perspective
AI summary Read the abstract
Researchers conducted a nationwide survey of microplastics in Chinese agricultural soils, collecting 477 samples from 109 cities across 31 regions, and identified spatial distribution patterns and key factors influencing farmland microplastic contamination.
Microplastics in China’s surface water systems: Distribution, driving forces and ecological risk
AI summary Read the abstract
Researchers compiled over 14,000 samples from across China to map microplastic pollution in surface water systems using machine learning models. They found that microplastic abundance varied enormously across regions, driven by a complex mix of human activities and natural conditions. The ecological risk assessment revealed that watersheds in nearly all Chinese provinces face high to extremely high contamination levels, underscoring the urgency of nationwide management efforts.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.