We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Predicting large-scale spatial patterns of marine meiofauna: implications for environmental monitoring
Summary
Researchers used machine learning to model the spatial distribution of marine meiofauna — small bottom-dwelling invertebrates — across the Santos Basin continental margin in Brazil, identifying six distinct benthic zones and providing a baseline for future environmental monitoring programs.
This study aims model the distribution of meiofauna indicators in relation to environmental variables from the Santos Basin continental margin, SE Brazil, using machine learning techniques, to provide baseline information and foster future monitoring programs. A total of 100 sampling stations were distributed in eight transects and 11 isobaths (25 to 2,400 m) perpendicular to the coast. In each station, three replicates were sampled for meiofauna and 38 environmental parameters. A total of 28 meiofauna taxa were found, with a mean richness varying from 3 to 15 taxa per station. Meiofauna mean density varied between 55 and 2,001 ind. 10 cm-2. Density of meiofauna and its most frequent taxa (Nematoda, Copepoda, Kinorhyncha, and Polychaeta), and taxa richness were used as descriptors for the models. Meiofauna and nematode density showed the highest training and testing accuracies, with R² values above 0.74. Based on the distribution of meiofauna descriptors and their responses to environmental conditions, we suggest a mosaic of six benthic zones. The La Plata Plume zone and the Cabo Frio Upwelling zone are two of the most diverse and productive zones in the continental shelf, wich are separated by the less productive Central Continental Shelf zone. A fourth zone, with very low meiofauna densities, corresponds to the carbonated sediments of the shelf-break. The Upper and Mid-Slope is a narrow zone along the entire basin, with intermediate densities and small amounts of high-quality organic carbon. The largest, impoverished zone, the Lower Slope and Plateau comprises the deepest areas and the São Paulo Plateau. The study showed that, although some zones can be recognized by most meiofauna descriptors, others are better characterized by specific ones, implying that meiofauna indicators should be monitored concomitantly. We recommend the optimization of sampling design based on our model to reduce costs and increase our understanding of the system.
Sign in to start a discussion.
More Papers Like This
Mapping the plastic legacy: Geospatial predictions of a microplastic inventory in a complex estuarine system using machine learning
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
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.
A Predictive Framework for Marine Microplastic Pollution using Machine Learning and Spatial Analysis
Researchers developed a machine learning framework integrated with geospatial analysis to predict microplastic pollution density across ocean regions. The Gradient Boosting model achieved the highest accuracy with 97% predictive performance, and spatial visualizations revealed pollution hotspots concentrated near industrial coastlines and major ocean current pathways.
Mapping the Plastic Legacy: Geospatial Predictions of a Microplastic Inventory in a Complex Estuarine System Using Machine Learning
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.
AI-Driven Framework Development for Predictive Classification of Microplastic Concentration of Aquatic Systems in the United States
Researchers compared four machine learning models—logistic regression, random forest, support vector machine, and a neural network—for predicting microplastic density in US coastal waters across three regions. The support vector machine performed best with 93.94% average accuracy, demonstrating the potential of AI-driven tools for microplastic monitoring.