Civil Engineering and Architecture Vol. 13(6), pp. 4508 - 4533
DOI: 10.13189/cea.2025.130628
Reprint (PDF) (1450Kb)

Sustainable Solutions: Advanced Analytics for Green Buildings Performance Using Machine Learning Models

Salam AL Kasassbeh ^1,*, Amani Abdallah Assolie ², Dareen Qashmar ³, Mai Aljaberi ^4
1 Department of Civil Engineering, Faculty of Engineering Technology, Al-Balqa Applied University, Jordan
² Department of Civil Engineering, Faculty of Engineering, Ajloun National University, Jordan
³ Department of Architecture, Faculty of Engineering, Al-Balqa Applied University, Jordan
⁴ Department of Civil Engineering, Faculty of Engineering, The Hashemite University, Jordan

ABSTRACT

The construction industry significantly impacts environmental sustainability through its consumption of natural resources, energy, and generation of waste. In response to rising environmental concerns and regulatory pressures, green building practices have emerged as a strategic solution to promote sustainable development. This study aims to evaluate the influence of four critical green building practices—green building materials, waste management, energy-efficient design, and innovative construction techniques—on the sustainability performance of construction projects in Jordan. Using a quantitative research approach, data were collected from 191 professionals across the Jordanian construction industry through structured questionnaires. To analyze the relationships between these practices and sustainability outcomes, the study employed Partial Least Squares Structural Equation Modeling (PLS-SEM), as well as machine learning techniques, including Random Forest and Gradient Boosting algorithms. The findings reveal that all four factors significantly contribute to enhancing sustainability performance, with energy-efficient design exerting the strongest influence. The Random Forest model demonstrated robust predictive performance, with an R² value of 0.78, indicating high accuracy in estimating sustainability scores. Moreover, the machine learning models allowed for interactive scenario analysis, enabling stakeholders to simulate the impact of each factor under varying implementation conditions. Practical implications of this study include providing policymakers and practitioners with data-driven recommendations for prioritizing sustainability initiatives and optimizing resource allocation. Socially, the research promotes awareness of sustainable construction practices and supports the development of environmentally responsible infrastructure. However, limitations include the focus on a single country context and reliance on self-reported data, which may influence generalizability. Future research should expand the dataset geographically and explore longitudinal impacts of green practices over time. Overall, this study contributes to the growing field of sustainable construction by integrating traditional statistical methods with artificial intelligence to provide a comprehensive evaluation framework.

KEYWORDS
Machine-Learning (ML), Sustainability, Green Buildings, Energy Efficiency, Waste Management, Innovative Construction Techniques

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Salam AL Kasassbeh , Amani Abdallah Assolie , Dareen Qashmar , Mai Aljaberi , "Sustainable Solutions: Advanced Analytics for Green Buildings Performance Using Machine Learning Models," Civil Engineering and Architecture, Vol. 13, No. 6, pp. 4508 - 4533, 2025. DOI: 10.13189/cea.2025.130628.

(b). APA Format:
Salam AL Kasassbeh , Amani Abdallah Assolie , Dareen Qashmar , Mai Aljaberi (2025). Sustainable Solutions: Advanced Analytics for Green Buildings Performance Using Machine Learning Models. Civil Engineering and Architecture, 13(6), 4508 - 4533. DOI: 10.13189/cea.2025.130628.