Xie Jiaxing, Liu Shun, Su Lihao, Zhao Xinting, Wang Yan, Tan Feng
Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China.
Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China.
Sci Total Environ. 2024 Dec 1;954:176575. doi: 10.1016/j.scitotenv.2024.176575. Epub 2024 Sep 27.
In this study, an optimized random forest (RF) model was employed to better understand the soil-water partitioning behavior of per- and polyfluoroalkyl substances (PFASs). The model demonstrated strong predictive performance, achieving an R of 0.93 and an RMSE of 0.86. Moreover, it required only 11 easily obtainable features, with molecular weight and soil pH being the predominant factors. Using three-dimensional interaction analyses identified specific conditions associated with varying soil-water partitioning coefficients (K). Results showed that soils with high organic carbon (OC) content, cation exchange capacity (CEC), and lower soil pH, especially when combined with PFASs of higher molecular weight, were linked to higher K values, indicating stronger adsorption. Conversely, low K values (< 2.8 L/kg) typically observed in soils with higher pH (8.0), but lower CEC (8 cmol/kg), lesser OC content (1 %), and lighter molecular weight (380 g/mol), suggested weaker adsorption capacities and a heightened potential for environmental migration. Furthermore, the model was used to predict K values for 142 novel PFASs in diverse soil conditions. Our research provides essential insights into the factors governing PFASs partitioning in soil and highlights the significant role of machine learning models in enhancing the understanding of environmental distribution and migration of PFASs.
在本研究中，采用了一种优化的随机森林（RF）模型，以更好地了解全氟和多氟烷基物质（PFASs）的土壤-水分配行为。该模型表现出强大的预测性能，R值为0.93，均方根误差（RMSE）为0.86。此外，它仅需要11个易于获取的特征，其中分子量和土壤pH值是主要因素。通过三维相互作用分析确定了与不同土壤-水分配系数（K）相关的特定条件。结果表明，有机碳（OC）含量高、阳离子交换容量（CEC）高且土壤pH值较低的土壤，特别是与较高分子量的PFASs结合时，与较高的K值相关，表明吸附更强。相反，在pH值较高（8.0）、CEC较低（8厘摩尔/千克）、OC含量较低（1%）且分子量较轻（380克/摩尔）的土壤中通常观察到的低K值（<2.8升/千克），表明吸附能力较弱，环境迁移潜力较大。此外，该模型用于预测142种新型PFASs在不同土壤条件下的K值。我们的研究为控制PFASs在土壤中分配的因素提供了重要见解，并突出了机器学习模型在增强对PFASs环境分布和迁移理解方面的重要作用。
