Using machine learning to reveal drivers of soil microplastics and assess their stock: A national-scale study,Journal of Hazardous Materials

当前位置： X-MOL 学术 › J. Hazard. Mater. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Using machine learning to reveal drivers of soil microplastics and assess their stock: A national-scale study
Journal of Hazardous Materials ( IF 12.2 ) Pub Date : 2024-08-10 , DOI: 10.1016/j.jhazmat.2024.135466
Linjie Zhang ₁ , Feng Wang ₁ , Wenyue Wang ₁ , Yinglong Su ₁ , Min Zhan ₁ , Jun Lu ₂ , Bing Xie ₃

Affiliation

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.

更新日期：2024-08-10

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南