Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach

Creative Commons License

Cakiroglu C., Aydin Y., BEKDAŞ G., Geem Z. W.

MATERIALS, vol.16, no.13, 2023 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 16 Issue: 13
  • Publication Date: 2023
  • Doi Number: 10.3390/ma16134578
  • Journal Name: MATERIALS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, CAB Abstracts, Communication Abstracts, Compendex, INSPEC, Metadex, Veterinary Science Database, Directory of Open Access Journals, Civil Engineering Abstracts
  • Istanbul University Affiliated: No

Abstract

Basalt fibers are a type of reinforcing fiber that can be added to concrete to improve its strength, durability, resistance to cracking, and overall performance. The addition of basalt fibers with high tensile strength has a particularly favorable impact on the splitting tensile strength of concrete. The current study presents a data set of experimental results of splitting tests curated from the literature. Some of the best-performing ensemble learning techniques such as Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Random Forest, and Categorical Boosting (CatBoost) have been applied to the prediction of the splitting tensile strength of concrete reinforced with basalt fibers. State-of-the-art performance metrics such as the root mean squared error, mean absolute error and the coefficient of determination have been used for measuring the accuracy of the prediction. The impact of each input feature on the model prediction has been visualized using the Shapley Additive Explanations (SHAP) algorithm and individual conditional expectation (ICE) plots. A coefficient of determination greater than 0.9 could be achieved by the XGBoost algorithm in the prediction of the splitting tensile strength.