This paper outlines the obstacles to sustainable construction growth in Iran and thereafter examines the effect and relation between these barriers and the direction of sustainable construction growth as one of the essential objectives for achieving sustainable cities and infrastructure. The study is applied for research purposes that are based on descriptive survey data gathering and correlational data analysis techniques. The statistical population for this study consists of 120 construction-related engineers and university professors who were assessed on a five-point Likert scale. Using SmartPLS software version 4, the responses to the questionnaire were examined. The Kolmogorov–Smirnov assessment was utilized to evaluate the normalcy of the variables, as this assessment is typically employed for this purpose. For data analysis, the PLS (partial least squares) method was used, while SEM (structural equation modeling) methods have been used to assess the study hypotheses. Cronbach’s alpha and the composite reliability coefficient (CR) were applied to determine the instrument’s viability, and the results show that the coefficient connected to all variables is above 7.0, which is an acceptable value. The AVE (average variance extracted) was also used to evaluate the questionnaire’s validity, which was greater than 0.4 and deemed acceptable for coefficients of significance (T-values), coefficient of predictive power (Q2), and coefficient of determination (R2). The obtained results support and confirm all research hypotheses, including that the identified obstacles directly affect the performance of sustainable construction. According to the results of the Friedman test, the legal restrictions variable (CL) is the most significant obstacle to sustainable construction in Iran, with a rank of 4.24. The indicators of political limits (CP) and social and cultural constraints (CSC) came in at second and third, respectively. The results could help government officials make better decisions about where to focus their attention and how to distribute scarce resources.

Recent developments in indirect predictive methods have yielded promising solutions for energy consumption modeling. The present study proposes and evaluates a novel integrated methodology for estimating the annual thermal energy demand (D_AN), which is considered as an indicator of the heating and cooling loads of buildings. A multilayer perceptron (MLP) neural network is optimally trained by symbiotic organism search (SOS), which is among the strongest metaheuristic algorithms. Three benchmark algorithms, namely, political optimizer (PO), harmony search algorithm (HSA), and backtracking search algorithm (BSA) are likewise applied and compared with the SOS. The results indicate that (i) utilizing the properties of the building within an artificial intelligence framework gives a suitable prediction for the D_AN indicator, (ii) with nearly 1% error and 99% correlation, the suggested MLP-SOS is capable of accurately learning and reproducing the nonlinear D_AN pattern, and (iii) this model outperforms other models such as MLP-PO, MLP-HSA and MLP-BSA. The discovered solution is finally expressed in an explicit mathematical format for practical uses in the future.