We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Mapping the plastic legacy with NIXVEGS: Machine-learning enabled microplastics prediction in sediments
AI summary Read the abstract
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.
Abstract 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.
More Papers Like This
Mapping the plastic legacy with NIXVEGS: machine-learning enabled microplastics prediction in sediments
AI summary Read the abstract
Researchers built a computer model called NIXVEGS to predict microplastic levels in riverbed and seabed mud, using sediment samples from the Schlei estuary in northern Germany. The model expanded usable data coverage over 7-fold and estimated the region's sediment holds about 20 trillion microplastic particles, roughly 14.3 tons.
Mapping the plastic legacy: Geospatial predictions of a microplastic inventory in a complex estuarine system using machine learning
AI summary Read the abstract
Researchers developed a machine learning approach called NIXVEGS — combining nested iterative cross-validation, ensemble modeling, and grid search techniques — to predict spatial microplastic inventories in the complex estuarine system of the Schlei in northern Germany, where hydrodynamic complexity from narrowings, freshwater tributaries, and brackish inflows challenges conventional models. They estimated 20 trillion microplastic particles, or 14.5 tonnes in the 50 to 5,000 micrometer range, residing in the upper sediments of the Schlei, representing the highest-resolution microplastic inventory for an entire geomorphological region.
Mapping the Plastic Legacy: Geospatial Predictions of a Microplastic Inventory in a Complex Estuarine System Using Machine Learning
AI summary Read the abstract
Researchers applied machine learning geospatial modelling to predict microplastic distribution across a complex estuarine system, using sediment samples as a training dataset to generate spatial inventory maps of microplastic accumulation. The model leveraged the estuary's role as a land-sea interface and plastic accumulation bottleneck to produce high-resolution predictions of microplastic hotspots for monitoring and management purposes.
Mapping the plastic legacy: Geospatial predictions of a microplastic inventory in a complex estuarine system using machine learning
AI summary Read the abstract
Researchers applied machine learning techniques to develop geospatial predictions of microplastic inventory in a complex estuarine system, overcoming the limitations of coarse ocean basin models by accounting for the intricate geomorphological and hydrodynamic conditions that govern sediment-associated microplastic distribution.
Microplastic Deposit Predictions on Sandy Beaches by Geotechnologies and Machine Learning Models
AI summary Read the abstract
Researchers used satellite imagery and machine learning to predict where microplastics accumulate on sandy beaches along Brazil's northern coast. They found that beach shape, slope, and proximity to urban areas were strong predictors of microplastic deposits. The study demonstrates that geotechnology tools can help identify pollution hotspots without costly field sampling at every location.
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.