Article
?
AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button.
Tier 2
?
Original research — experimental, observational, or case-control study. Direct primary evidence.
Environmental Sources
Marine & Wildlife
Policy & Risk
Sign in to save
Mapping the plastic legacy with NIXVEGS: Machine-learning enabled microplastics prediction in sediments
2026
Score: 40
?
0–100 AI score estimating relevance to the microplastics field. Papers below 30 are filtered from public browse.
Knowing how many microplastic particles are buried in estuarine sediments is important for managing coastal pollution, but direct sampling is sparse and expensive. Researchers developed NIXVEGS, an open-source machine-learning pipeline that predicts microplastic distribution across an estuary using sediment grain size and spatial connectivity as proxies. Applied to a German Baltic Sea estuary, the model increased spatial data coverage more than sevenfold and estimated the total sediment microplastic inventory at roughly 20 trillion particles, or about 14 tonnes. Tools like this can help policymakers set realistic cleanup targets and track whether pollution levels are improving over time.
Study Type
Environmental
<title>Abstract</title> Aquatic sediments act as major sinks for microplastic (MP) pollution, yet accurately quantifying their MP distributions and inventories on a regional scale remains challenging, especially in hydrodynamically complex estuarine environments. Existing distribution models focus on ocean basins or simple hydrodynamic systems but lack sufficient adaptability to the spatial heterogeneity typical of estuaries. To address this limitation, we developed NIXVEGS, an open-source empirical spatial prediction pipeline adapting machine learning components like nested cross-validation and ensemble modeling specifically for the sparse data characteristic of environmental MP studies. It integrates granulometric proxies and spatio-temporal connectivity to predict MP distributions and provides data-driven decisions in model selection combined with performance validation on unseen data under the best possible utilization of the available observations. The model predictions increased spatial data coverage 7.6-fold from an original set of 26 analyzed MP sediment concentration in the Schlei estuary (Baltic Sea coast, Northern Germany). We demonstrate the application of NIXVEGS and use its predictions to estimate the region’s sedimentary MP inventory at ~ 20 trillion particles (50-5000 µm) or ~ 14.3 tons. Estuarine sediments are key environments for monitoring MP pollution evolution, where NIXVEGS can assist regional plastic management and contribute to the understanding of a global MP budget.