Machine learning predicts asphalt concrete strength using SHAP analysis

Researchers have developed a machine learning framework to predict the splitting strength of asphalt concrete, utilizing 296 samples and 14 input variables. Six models were compared, with TabPFN demonstrating the best performance, achieving an R^2 of 0.88 and a composite score of 0.91. SHAP analysis identified key variables influencing the strength, and optimal parameter ranges were quantified to improve the material's performance. A graphical user interface was also created to make the framework more accessible. AI

IMPACT This research demonstrates the application of advanced machine learning techniques for material science, potentially improving construction material design and performance.

RANK_REASON The item is an academic paper detailing a machine learning model for a specific engineering application. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Ag4.75
• Ag9.5
• artificial neural network
• LightGBM
• Shap
• Support Vector Regression
• TabPFN
• University of Denver
• XGBoost

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →