Unraveling the Context-Dependent Effects of Microplastics on Soil Enzymatic Activities via Interpretable Machine Learning
- 1Hainan Province Key Laboratory of One Health, Collaborative Innovation Center of Life and Health, School of Life and Health Sciences, Hainan University, Haikou 570228, China
Abstract
Microplastics (MPs) increasingly accumulate in agricultural soils, yet their effects on soil enzymatic activity remain heterogeneous. Here, a literature-derived dataset was analyzed using an interpretable machine learning framework. eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) captured non-linear patterns in enzymatic responses to MP characteristics. Particle size showed the strongest model-based contribution, with a dataset-derived size-sensitive range of 200–600 μm associated with more pronounced predicted inhibition. Dosage showed a plateau-like pattern above approximately 100 g/kg, while exposure time exhibited non-linear variation across the observed duration. SHapley Additive exPlanations (SHAP) analysis further characterized the relative contributions of individual features to model predictions. Overall, the results provide quantitative, data-driven insights into heterogeneous MP-soil enzyme associations and highlight particle size as an important factor for further experimental investigation and risk assessment.
Related
- Microplastics in the rhizosphere: unraveling plant–microbe–soil interactions and consequences for crop resilience
- Shape-dependent polyurethane microplastics reprogram root architecture and detoxification modules to suppress cadmium uptake in a hyperaccumulator
- Varying Seasonal Runoff Drives the Timing and Volume of Water‐Dependent Recreational Activities in the Sacramento‐San Joaquin Delta
- Microbial Inoculant‐Driven Degradation of Microplastics Associated With Garbage Environment and Assessment of Degradation Product Toxicity
- Bioflocculation of polystyrene microplastics using dried Nostoc spp. biomass: laboratory performance, response modeling, and mechanistic assessment
BibTeX
@article{liu2026unraveling,
title = {{Unraveling the Context-Dependent Effects of Microplastics on Soil Enzymatic Activities via Interpretable Machine Learning}},
author = {Zifei Liu and Yitong Liu and Tianpeng Wang and Juanjuan Li and Xue Chi and Hong Li},
journal = {Biology},
year = {2026},
month = oct,
doi = {10.3390/biology15201880},
url = {https://europepmc.org/article/PMC/PMC13701847},
note = {CC BY},
}
RIS
TY - JOUR
TI - Unraveling the Context-Dependent Effects of Microplastics on Soil Enzymatic Activities via Interpretable Machine Learning
AU - Zifei Liu
AU - Yitong Liu
AU - Tianpeng Wang
AU - Juanjuan Li
AU - Xue Chi
AU - Hong Li
PY - 2026
DA - 2026/10/01
JO - Biology
DO - 10.3390/biology15201880
UR - https://europepmc.org/article/PMC/PMC13701847
AB - Microplastics (MPs) increasingly accumulate in agricultural soils, yet their effects on soil enzymatic activity remain heterogeneous. Here, a literature-derived dataset was analyzed using an interpretable machine learning framework. eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) captured non-linear patterns in enzymatic responses to MP characteristics. Particle size showed the strongest model-based contribution, with a dataset-derived size-sensitive range of 200–600 μm associated with more pronounced predicted inhibition. Dosage showed a plateau-like pattern above approximately 100 g/kg, while exposure time exhibited non-linear variation across the observed duration. SHapley Additive exPlanations (SHAP) analysis further characterized the relative contributions of individual features to model predictions. Overall, the results provide quantitative, data-driven insights into heterogeneous MP-soil enzyme associations and highlight particle size as an important factor for further experimental investigation and risk assessment.
SN - 2079-7737
ER -