We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A new modeling approach for microplastic drag and settling velocity
AI summary Read the abstract
Researchers developed a novel machine learning-based modelling framework to predict drag coefficients and settling velocities for microplastics of varying shapes (1D, 2D, 3D, and mixed) in aquatic environments. The framework achieved coefficient of determination values of 0.86-0.95 for drag models, outperforming traditional theoretical and data-fitting approaches in both speed and accuracy.
Understanding microplastics' (MPs') transport and settling behaviors in aquatic environments is crucial for devising effective management strategies. This study contributes a novel modeling framework to develop accurate and interpretable drag and velocity models for MPs using machine learning techniques. It achieves faster model creation and improved accuracy than traditional methods like theoretical analysis and data fitting. The framework demonstrates high predictive accuracy across different MP types (1D, 2D, 3D, and mixed), with a coefficient of determination CD = 0.86-0.95 for the drag models and CD = 0.92-0.95 for the velocity models. Compared with best-performing empirical approaches, the new drag models exhibit an average reduction in root mean square error (RMSE) by 59% and mean absolute error (MAE) by 62%. Similarly, the velocity models show a mean decrease in RMSE and MAE by 27% and 25%, respectively. Moreover, the framework outperforms commonly used symbolic regression methods, reducing errors by 18%-27%. The sensitivity analysis reveals that the relative density difference and the dimensionless diameter are essential for predicting the settling of all MP types, while the effective shape parameters vary across different MP categories. By providing accurate predictions of MPs' settling dynamics, this study offers insights for developing targeted mitigation strategies to reduce MPs' environmental impacts.
More Papers Like This
Prediction of Settling Velocity of Microplastics by Multiple Machine-Learning Methods
AI summary Read the abstract
Researchers developed machine learning models to predict the settling velocity of microplastics in water, using particle shape, size, and density as inputs. The models outperformed traditional empirical equations, providing a more accurate tool for modeling microplastic transport and sedimentation.
Machine learning-based prediction for settling velocity of microplastics with various shapes
AI summary Read the abstract
Researchers developed machine learning models to predict the settling velocity of microplastics based on their size, density, and shape. They classified microplastic shapes into fiber, film, and fragment categories and identified the optimal shape parameter for each, achieving significantly better prediction accuracy than existing theoretical models. The study reveals that particle size has the greatest influence on settling velocity, which is important for understanding how microplastics move and distribute in water environments.
Towards A universal settling model for microplastics with diverse shapes: Machine learning breaking morphological barriers
AI summary Read the abstract
Researchers developed a machine learning model to predict the settling velocity of microplastics across different shapes, including fragments, films, and fibers. Unlike existing models limited to specific morphologies, this approach works universally across all three particle types. The study provides a more reliable tool for modeling how microplastics move through and deposit in aquatic environments.
Improved Settling Velocity for Microplastic Fibers: A New Shape-Dependent Drag Model
AI summary Read the abstract
A new shape-dependent drag model was developed to improve the accuracy of settling velocity predictions for microplastic fibers, addressing a major limitation of existing drag models that significantly underpredict fiber settling in aquatic environments.
Dynamic prediction of large spherical and cylindrical microplastic deposition: a machine learning approach for transport and deposition
AI summary Read the abstract
Researchers developed a machine learning model combined with dimensionless analysis to predict the deposition patterns of spherical and cylindrical microplastics in aquatic environments. The model accounts for varied flow conditions and particle shapes to improve predictions of where microplastics settle in water bodies. The study offers a practical tool for pollution monitoring efforts by helping predict microplastic accumulation hotspots in rivers and oceans.
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.