Due to its substantial energy use, greenhouse gas emissions, and resource depletion, the construction sector is one of the biggest causes of environmental deterioration. Sustainable building techniques have become a vital strategy for mitigating these issues and lowering the environmental impact of civil engineering projects. Green buildings are ones that preserve or enhance the local standard of living via the use of sustainable construction techniques. Artificial Intelligence (AI) in Green Construction is used to analyse data collected from monitoring the construction site and utilising predictive analytics to make decisions that impact a project's quality, safety, profitability, and timeline. The goal of the planned study was to assess the potential for AI in Green Building Construction (AI-GBC) to lower utility costs and carbon emissions. RF and GA are used by artificial intelligence to lower carbon dioxide emissions and energy consumption. The accuracy of the AI-GBC is assessed using a number of statistical measures, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Root Mean Squared Log Error (RMSLE). With prediction accuracies over 96%, both Machine Learning (ML) models produced favourable outcomes. With an R2 of 0.96, GA models performed rather well in terms of predicting Co_2. 98% will undertake a k-fold cross-validation analysis, and 96% will finish a performance analysis. In order to avoid overfitting and guarantee the accuracy of the results obtained from the extended modelling technique, cross-validation is employed. © 2025 Elsevier B.V., All rights reserved.