We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Deciphering Soil Hydro-Physical Controls on Microplastic Fate Using Explainable Machine Learning
AI summary Read the abstract
Scientists studying orchard soils in Turkey found that tiny bits of plastic build up differently depending on how farmland is managed and what the soil is made of, soils rich in organic matter, with certain textures and water-holding traits, tend to trap more microplastics rather than letting them wash away. This matters because these soils grow our food, and understanding where microplastics get stuck (versus moving into groundwater or crops) could help farmers and regulators reduce the amount of plastic contamination that eventually reaches our plates and water supplies.
Understanding the environmental fate of microplastics (MPs) in agricultural soils remains a major challenge, particularly under field conditions where soil structure and hydraulic processes jointly regulate particle transport and retention. This study investigated whether hydro-physical soil functioning can explain the distribution and accumulation of MPs in pistachio orchard soils from a semi-arid region of southeastern Türkiye. A total of 42 soil samples were analyzed for MP abundance, size distribution, and morphology, together with key hydro-physical properties including texture, porosity, bulk density, aggregate stability, organic matter content, and soil water retention characteristics. To identify the dominant controls on MP occurrence, explainable machine learning approaches combining Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and SHAP (SHapley Additive exPlanations) analysis were employed. Microplastic abundance differed among management systems. Former landfill or construction sites represented the largest proportion of the total recorded microplastic abundance (40.9%), followed by conventionally managed (25.2%), manure-amended (24.5%), and sewage-sludge-amended orchards (9.4%). Median microplastic abundances were 1433, 667, 4633, and 633 particles kg−1 soil, respectively. Fine-sized MPs constituted the dominant particle fraction and exhibited strong associations with pore-system characteristics, indicating that pore-size compatibility governs their retention and mobility within the soil matrix. Morphology-specific analyses further revealed contrasting relationships between soil hydro-physical properties and individual MP forms, suggesting distinct retention pathways for granules, films, fragments, and fibers. Explainable AI analysis identified organic matter, silt content, bulk density, and water retention characteristics as the most influential predictors of MP occurrence. Among the tested models, RF demonstrated superior predictive robustness and generalization capacity. The findings demonstrate that hydro-physical soil functioning plays a central role in determining microplastic fate in agricultural soils and highlight the value of interpretable machine learning frameworks for uncovering the mechanisms underlying contaminant retention and redistribution. Integrating soil structural indicators with explainable artificial intelligence offers a promising pathway for improving microplastic risk assessment in agroecosystems.
More Papers Like This
Machine learning prediction and interpretation of the impact of microplastics on soil properties
AI summary Read the abstract
Researchers applied machine learning models to predict how microplastics affect soil properties, finding that microplastic release into soils is 4 to 23 times higher than into oceans. The models identified key factors influencing soil changes, including microplastic type, size, and concentration, as well as soil texture. The study suggests that machine learning can help address the complexity of soil-microplastic interactions and improve predictions of environmental impacts.
Interpretable machine learning reveals transport of aged microplastics in porous media: Multiple factors co-effect
AI summary Read the abstract
Using machine learning, researchers discovered that microplastics that have been weathered by sunlight and environmental exposure move through soil significantly faster than fresh ones. The aging process changes the plastic surface chemistry, making particles more mobile and more likely to reach deeper soil layers and groundwater. This means microplastics in agricultural soil and landfills may contaminate underground water supplies more quickly than previously thought.
Soil Physical Structure Controls Microplastic Accumulation and Partitioning in Pistachio Orchards
AI summary Read the abstract
Scientists found that the physical makeup of soil, like how compact or crumbly it is, affects how much tiny plastic pollution (microplastics) builds up in farm soil, using pistachio orchards as an example. This matters because microplastics in soil can end up in the food we grow and eventually in our bodies, so understanding what causes them to accumulate could help farmers manage land in ways that reduce that contamination.
Machine learning-driven estimation of microplastic percentage yield for rapid and accurate quantification
AI summary Read the abstract
Scientists used artificial intelligence to make it faster and more accurate to measure how much microplastic is actually in soil samples—a process that's historically been tricky and inconsistent. This matters because microplastics in farm soil can end up in our food and water, so having reliable measurement tools helps researchers better track contamination and understand potential risks to human health. While this study focuses on lab methods rather than health effects directly, better detection is a key step toward understanding how much plastic pollution we're really exposed to.
Explainable Machine Learning for Soil Health Index Prediction and Degradation-Risk Screening: A Synthetic Multi-Region Proof-of-Concept for Circular-Bio-economy Soil Management
AI summary Read the abstract
Researchers built a computer model (using simulated, not real-world, data) to test whether AI can predict soil health and flag "at-risk" soil by looking at factors like organic carbon, moisture, and even microplastic contamination. The tool worked well in this test setting and pointed to microplastics as one of several important factors tied to declining soil quality, a useful early step toward tools that could one day help farmers protect the soil that grows our food. Since the data was artificially generated, these results are a proof-of-concept, not proof the model works on real farmland yet.
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.