Reinforced Concrete Design with Geopolymer Concrete in Construction Management and Neural Networks

This paper presents an integrated approach combining reinforced concrete design, geopolymer concrete (GPC) technology, construction management principles, and artificial neural networks (ANNs). Geopolymer concrete, synthesized through the alkaline activation of aluminosilicate precursors, provides a sustainable alternative to ordinary Portland cement (OPC) by significantly reducing CO₂ emissions while maintaining comparable or superior mechanical and durability characteristics. The study highlights the role of construction management in facilitating the adoption of GPC, focusing on risk mitigation, material optimization, and lifecycle cost efficiency. Artificial neural networks were employed to model and predict the compressive strength of fly ash- and slag-based GPC mixtures using key input variables such as activator concentration, curing temperature, and precursor ratios. A Bayesian regularization algorithm yielded the most accurate prediction results, achieving correlation coefficients above 0.8 and a mean square error of 0.0057. The integration of ANN-based predictive models within construction management frameworks enhances decision-making in material selection, project scheduling, and cost estimation. Furthermore, the implementation of geopolymer concrete in large-scale projects, exemplified by the Raden Inten II bridge, demonstrates its structural reliability and environmental benefits. The findings underscore the synergistic relationship between sustainable material innovation, digital construction management, and machine learning applications, offering a pathway toward resilient and carbon-neutral infrastructure development.