Quality Assurance Revolution in Fly Ash-Based Sustainable Building: Advance Modeling Techniques and Innovative Application

The global supply of Class F fly ash from bituminous coal is declining as nations shift to renewable energy. Coal-fired plants now use subbituminous coals, producing Class C fly ash or mixtures to cut emissions and costs. This study examines quality control in sustainable construction, focusing on optimizing fly ash mixtures for better quality, cost
efficiency, lower carbon footprints, and improved concrete strength. Using six machine learning techniques, including XGBoost and Random Forest, the research analyzed 1,030 entries of compressive strength data. Rigorous validation included R-squared (R2), adjusted R2, mean absolute error, and root mean square error. XGBoost and Random Forest models achieved predictive R2 values of 92% and 91%, respectively. This study refines quality control in eco-friendly construction materials base on fly ash approach, achieving favourable outcomes with the Concrete Strength Lab Calculator Application using XGBoost, advancing sustainable construction methodologies.

Keyword: Compressive strength; Carbon footprint Environmental sustainability; Machine learning techniques; Quality assurance.