Optimizing Cost Performance in Green Industrial Palm Oil Projects Using AI-Based AEC

This study investigates green industrial palm oil project cost performance determinants through Artificial Intelligence (AI)-based Architecture, Engineering, and Construction (AEC) systems. The study employed a Structural Equation Modeling Partial Least Squares (SEM-PLS) approach to analyze significant data collected from 115 respondents through 166 validated indicators. Ten primary drivers were identified, and alternative water sources topped the list, followed by indoor air quality auditing, green material, and smart metering systems, all of which were identified as primary cost-effectiveness drivers. Simulations of Green Mark certification levels (Gold, Gold Plus, and Platinum) indicated potential cost savings of 7.01% to 7.05%. The model continued to have very good predictive capability with an R² value of 0.791, testifying to the robustness of the methodology presented. The results validate the engineering value of AI-aided AEC in cost performance maximization and enhancement in eco-friendly industrial building. The findings also offer practical suggestions for design, planning, and execution of cost-saving, eco-friendly palm oil mills.