We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Explainable machine learning for predicting microplastic burden in commercially important freshwater fish and assessing dietary exposure
AI summary Read the abstract
Researchers measured microplastics in the digestive tracts of four fish species sold at markets in Yichang, China, and used a computer model to predict microplastic levels based on fish size, species and market. Fish weight and length were the strongest predictors, and most plastic pieces found were fibers made of common plastics like polypropylene and polyethylene. Based on these measurements, the study estimated a yearly dietary exposure figure for adult men, noting this is a conservative upper estimate.
Microplastic (MP) contamination in commercially important freshwater fish represents an emerging concern for aquatic ecosystem integrity and human food safety. This study presents an interpretable machine learning framework for predicting and assessing MP accumulation in European sea bass (Dicentrarchus labrax), Nile tilapia (Oreochromis niloticus), bighead carp (Hypophthalmichthys nobilis) and crucian carp (Carassius auratus) collected from four retail markets in Yichang City, Hubei Province, China. A total of 480 fish specimens generated 980 analytical records following gastrointestinal tract (GIT) extraction by alkaline digestion using 10% potassium hydroxide (KOH). Recovered MPs were characterised using attenuated total reflectance Fourier-transform infrared (ATR-FTIR) spectroscopy and scanning electron microscopy coupled with energy-dispersive X-ray spectroscopy (SEM-EDS). Six supervised regression algorithms, namely XGBoost, LightGBM, CatBoost, Random Forest, Support Vector Regression (SVR) and Artificial Neural Network (ANN), were evaluated using an 80:20 stratified training–testing split (784/196 records). XGBoost achieved the highest predictive performance (R2 = 0.96, RMSE = 0.48 MPs kg−1) and was selected as the optimal model. SHapley Additive exPlanations (SHAP) identified fish weight, total length, market of origin and species as the principal predictors of MP burden. Polypropylene (PP), polyethylene (PE) and polystyrene (PS) predominated, with fibres representing the dominant morphology. Estimated dietary exposure reached approximately 4,650 particles year−1 for adult males, while 32% of fish exceeded 0.04 MPs g−1 wet weight. Because MPs were measured exclusively in GIT tissue, this estimate represents a conservative upper-bound approximation of dietary exposure.
More Papers Like This
Machine learning-based assessment of microplastic pollution and human dietary risk in four commercial markets fish species from Yichang, China
AI summary Read the abstract
Researchers tested four popular fish types sold in Chinese markets, including sea bass and tilapia, and found tiny plastic particles called microplastics in all of them, with sea bass containing the most. Bigger fish tended to have more plastic buildup, and men who eat these fish regularly may be exposed to more microplastics than women simply due to typically eating larger portions. This study is a reminder that the fish on our dinner plates can carry plastic pollution, adding to calls for better regulation to keep contaminants out of our food supply.
Machine learning reveals drivers of microplastic bioaccumulation in fish from a freshwater reservoir ecosystem
AI summary Read the abstract
Researchers applied a two-phase machine learning approach to microplastic bioaccumulation data from 150 fish across three feeding strategies in an Iranian reservoir, finding that feeding strategy and body size are the strongest biological predictors, while particle shape, color, and polymer richness substantially improve characterization of exposure profiles when incorporated into ensemble models.
Influence of microplastics on the bioavailability of organic pollutants in freshwater sediments: a data-driven modeling study
AI summary Read the abstract
Scientists used machine learning to study how tiny plastic particles in river and lake sediment affect the way other pollutants (like industrial chemicals) behave in the environment. They found that very small microplastics (30-100 micrometers) and certain common plastic types, like those found in packaging and clothing, make it easier for these pollutants to become "available," meaning they can more easily enter the food chain through fish and other wildlife. This matters because it suggests microplastic pollution isn't just a standalone problem, it may actually make other environmental toxins more likely to build up in the ecosystem we ultimately eat from.
Intake of microplastics by commercial fish: A Bayesian approach
AI summary Read the abstract
Using a Bayesian statistical approach, this study estimated microplastic ingestion rates in commercial fish from urban Brazilian water bodies, linking fish microplastic burden to proximity of human settlement and plastic disposal practices.
Machine Learning-Driven Prediction of Organic Compound Adsorption onto Microplastics in Freshwater
AI summary Read the abstract
Seven machine learning algorithms were trained on 173 published measurements to predict how strongly organic contaminants adsorb onto different types of microplastics in freshwater. Accurate adsorption predictions are essential for assessing environmental risk, because microplastics that strongly bind pollutants become vectors that concentrate and transport toxic chemicals through aquatic food webs.
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.