Machine Learning-Driven Strength Prediction and Sustainability Analysis of Ultra-High-Performance Concrete

Ultra-high-performance concrete (UHPC) is recognized for its exceptional strength and durability. However, the adoption of UHPC frequently leads to higher material and environmental costs. Accurate prediction of compressive strength is crucial for optimizing material design and reducing construction costs. In this study, a dataset of 800 samples was compiled from published articles. Four models, including random forest (RF), Gaussian Process Regression (GPR), Gradient Boosting (GB) and Artificial Neural Network (ANN), were applied. Results show that ANN and GPR achieved the best accuracy and stability. GB also performed well with good adaptability. RF captured general trends but produced larger errors in the high-strength range. Feature importance analysis highlighted curing age and cement content as the most influential factors, with a combined contribution above 65%. The water-to-binder ratio also affected strength through matrix densification. Extended evaluation with regression error characteristic (REC) curves and environmental impact index (EII) revealed the balance between performance and environmental impact. Higher compressive strength often required higher energy, CO₂, and resource use. The range of 150-250 MPa showed a better balance between performance and sustainability. This study confirms the robustness of machine learning models for strength prediction and provides guidance for green and low-carbon ultra-high-performance concrete design.