Research Information System
Energy and Buildings, vol.318, 2024 (SCI-Expanded)
Hospital buildings incur significant energy consumption due to their expensive operations, advanced medical equipment, strict sanitation protocols, and compliance with environmental standards in various weather conditions. For this study, focusing on two distinct climate regions in Turkey—Aksaray and Bursa provinces—a total of 1,440 unique scenarios were generated. These scenarios utilized materials from the Revit Building Information Modeling (BIM) software library, incorporating variations in thermal transmittance coefficients, solar heat gain coefficients, and building orientation angles. The research employed machine learning algorithms to predict energy consumption, carbon dioxide (CO2) emissions, total expenditures, and life cycle costs. While the Revit BIM software library provides numerous combinations of building materials, it's important to note that only a limited subset undergoes practical testing during construction. The main objective is to streamline the estimation of energy consumption, CO2 emissions, overall costs, and life cycle expenditures in similar architectural settings and under comparable climate conditions, eliminating the need for drafting and energy calculation software. Across all machine learning algorithms, predictions generated by artificial neural networks closely aligned with actual values. Notably, the R-squared (R2) values, a critical evaluation metric, produced the following outcomes: both R2 values for energy were 0.95; total costs achieved 0.93 and 0.97; CO2 emissions attained 0.94 and 0.97; and life cycle costs garnered 0.95 and 0.94 for validation and test datasets, respectively. These results suggest that the successes observed in the two provinces can be extrapolated to data from all regions in Turkey. Moreover, our model is capable of predicting energy consumption, costs, and CO2 emissions based on thermal transmittance values complying with the Turkish standard TS 825 and building orientation angles.