Explainable machine learning with a graphical user interface for estimating compressive strength and life cycle assessment based embodied carbon of rice husk ash concrete

Meeting the growing demand for concrete while reducing its environmental impact remains a crucial challenge for the construction industry. Although rice husk ash (RHA) offers substantial potential as a supplementary cementitious material to lower cement-related emissions, its widespread adoption is constrained by uncertainty in achieving a performance-environmental efficiency trade-off between mechanical performance and embodied carbon reduction. This paper proposes an explainable machine learning (ML) framework for the evaluation of compressive strength of RHA-based concrete across various curing stages, complemented by life cycle assessment (LCA) based embodied carbon evaluation. A refined database compiled from existing studies was adopted to train and optimise eight different ML models. The models were optimised using Optuna and assessed using multiple performance metrics, while SHapley Additive exPlanation (SHAP) was adopted to quantify global and local feature contributions. To support practical deployment, the best performing models were incorporated within an interactive decision support interface facilitating real time, coding free compressive strength prediction together with LCA-based embodied carbon calculation; thereby supporting performance-based mix design and accelerating the sustainable use of agricultural waste derived cementitious materials.