We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Evaluating the mechanical behavior of plastic waste modified asphalt using optimized machine learning approaches
AI summary Read the abstract
Researchers developed machine learning models optimized with Particle Swarm Optimization to predict mechanical properties of plastic-modified asphalt mixtures, finding that an XGBoost model achieved strong accuracy and that optimal performance occurred with plastic particle sizes of 2.5-4 mm and plastic content of 20-30%, offering a data-driven approach for sustainable pavement design using recycled plastics.
The growing environmental challenges associated with plastic waste disposal and the need for sustainable pavement construction practices have prompted significant research interest in incorporating recycled plastics into asphalt mixtures. However, accurately predicting the performance characteristics of plastic-modified asphalt mixtures, particularly Marshall Stability (MS) and Marshall Flow (MF), remains a critical yet challenging task due to complex nonlinear relationships between mixture constituents. This study addresses this issue by developing reliable predictive models using machine learning techniques including Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM), further optimized through Particle Swarm Optimization (PSO). A comprehensive dataset comprising 210 samples of plastic-modified asphalt mixtures was utilized, incorporating inputs such as plastic content and size, bitumen content, maximum aggregate size, mixing temperature, and compaction effort (number of blows), to predict MS and MF as outputs. Results showed that the PSO-optimized XGB model achieved the highest accuracy, yielding R2 values of 0.82 for MS and 0.83 for MF. Model interpretability was enhanced using advanced techniques such as SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDP), Individual Conditional Expectation (ICE) plots, and Taylor diagrams, quantitatively highlighting optimal plastic particle sizes (2.5-4 mm), bitumen content (5.3-5.5%) and plastic content (20-30%). These findings provide actionable insights that support safer and longer-lasting pavements, promote the sustainable reuse of waste plastics, and enable cost-effective mix design strategies for modern asphalt construction.
More Papers Like This
A Systematic Literature Review of Machine Learning, Deep Learning, and Explainable AI for Predicting Mechanical Performance and Microplastic Release in Plastic Waste-Modified Asphalt
AI summary Read the abstract
This review of 36 studies looked at computer models that predict how well asphalt mixed with recycled plastic performs and how much microplastic it might release. Most studies focused only on strength and durability, with few examining microplastic release or explaining how the models made predictions, pointing to gaps for future research.
Applied machine learning multi-model benchmarking to plastic waste pyrolysis for optimizing crude oil yield production
AI summary Read the abstract
Researchers benchmarked 18 supervised machine learning algorithms against 754 plastic pyrolysis experiments using a leakage-free pipeline, finding Random Forest achieved the best clean performance (R²=0.74) and that Particle Swarm Optimization of reactor conditions nearly tripled crude oil liquid fraction yield from 20% to 56.95%.
Optimization of Asphalt Concrete Performance Using Waste Plastic Bottles (WPB) as a Sustainable Bitumen Modifier: A Comprehensive Rheological and Mechanical Assessment
AI summary Read the abstract
Not relevant to microplastics — this study evaluates waste plastic bottles as a bitumen modifier to improve asphalt road performance, testing mechanical and thermal properties; it addresses plastic reuse in construction rather than environmental microplastic pollution.
Machine Learning Predictions of Oil Yields Obtained by Plastic Pyrolysis and Application to Thermodynamic Analysis
AI summary Read the abstract
Researchers used machine learning, particularly XGBoost, to predict oil yields from plastic pyrolysis based on feed composition and reaction conditions, achieving a mean absolute error of 9.1% and demonstrating how the model can guide recycling strategies by identifying optimal plastic stream compositions.
Machine Learning in Predicting Outcomes of Brain Tumor Resection Surgeries: A Scholarly Review
AI summary Read the abstract
This review paper summarizes existing research on using recycled plastic in road pavement as an alternative to landfill disposal. It found mixed results: some plastic additives improved road durability, but storage stability problems and unclear long-term environmental effects, including plastic particle release, remain unresolved.
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.