Tariq, Zeeshan, Bahadori-Jahromi, Ali ORCID: https://orcid.org/0000-0003-0405-7146, Room, Shah and Al Tekreeti, Marwah (2026) Explainable Machine Learning Framework for strength prediction of sustainable concrete incorporating industrial waste SCMS with an embodied impact assessment. Sustainability, 18 (12).

PDF Explainable Machine Learning Framework for Concrete June 2026.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

Concrete contributes significantly to global CO₂ emissions due to high energy demand for cement production. This research integrates multiple advanced ensemble ML-based prediction models by combining experimental evaluation, explainable framework, and life cycle sustainability analysis for SCM-incorporated concrete mixtures. A comprehensive experimental program was conducted to evaluate the compressive and tensile strength of concrete, revealing that the hybrid mix of GF4 with a 40% replacement level of cement with fly ash and ground granulated blast furnace slag exhibited optimum synergistic performance. The study used k-fold cross-validation, PSO and Bayesian optimisation, and SHAP interpretation. XGBoost performed best for compressive strength, improving from R² = 0.879 to 0.918 after PSO optimisation. Gradient Boosting was selected for tensile strength, improving from R² = 0.840 to 0.879 after PSO optimisation. The life-cycle assessment showed that the GF4 mix reduced embodied carbon by 36% compared with the control mix, indicating strong potential for low-carbon concrete applications.

Item Type:	Article
Identifier:	10.3390/su18125848
Keywords:	sustainability; concrete; ground granulated blast furnace slag; fly ash; compressive strength; machine learning; SHAP analysis; environmental impact
Subjects:	Computing > Intelligent systems Construction and engineering
Date Deposited:	11 Jun 2026
Dates:	Date Publication status 27 April 2026 Submitted 4 June 2026 Accepted 8 June 2026 Published
School, department or research centre:	School of Computing and Engineering
Keywords:	sustainability; concrete; ground granulated blast furnace slag; fly ash; compressive strength; machine learning; SHAP analysis; environmental impact
URI:	https://repository.uwl.ac.uk/id/eprint/15032
Sustainable Development Goals:	Goal 9: Industry, Innovation, and Infrastructure	Sustainable Development Goals:	Goal 11: Sustainable Cities and Communities	Sustainable Development Goals:	Goal 12: Responsible Consumption and Production	Sustainable Development Goals:	Goal 13: Climate Action

Actions (admin access)