Challenges with hard-to-learn data in developing machine learning models for predicting the strength of multi-recycled aggregate concrete

Abstract

Research on multi-recycled aggregate concrete (MRAC), which involves reusing recycled concrete, has been actively pursued to promote sustainable practices. However, studying the properties of MRAC often requires significant time and resources. Machine learning (ML)-based predictive methods offer a promising solution to overcome these challenges. In this study, ML models were developed and evaluated to predict the compressive strength of MRAC using a dataset of 197 samples, 8 input features, grid search, cross-validation, and 9 algorithms. The results demonstrated that ML models could achieve high accuracy (R² > 0.9) even without the application of advanced techniques. However, certain data points consistently exhibited high error rates across multiple models, and the potential causes of poor performance associated with these data points were investigated. Additionally, a post-analysis of the evaluated models was conducted using Shapley Additive Explanations to assess the effect of key features, and recommendations were provided for improving MRAC properties for future research.