The U.S. Green Building Council’s (USGBC) Leadership in Energy and Environmental Design (LEED) certification program supports sustainable construction as part of the effort to address climate change and resource depletion. It is the world’s most popular green building certification system, with more than 146,400 projects. Satisfying the LEED requirements brings many benefits to a project’s design performance and adds community value, but it does incur additional costs and challenges. This study examined the choices made by those working on the 222 LEED New Construction version 4 (LEED-NC-V4) projects that were certified between September 2014 and March 2020 to determine how the LEED project teams selected appropriate LEED goals. The results reveal interesting insights into the way project LEED goals and the credits corresponding to the target certification level were chosen, as well as the links and trade-offs between the various credit options. Based on these findings, useful suggestions are made for ways to help LEED project teams achieve their target certification levels and encourage authorities to continue to improve their local green regulations. The analysis of actual certified projects’ data makes it possible to re-evaluate the effects of newly updated requests in LEED v4 in the light of the stated goals of the USGBC.

In recent years, machine learning models have become a potential approach in accurately predicting the concrete compressive strength, which is essential for the real-world application of geopolymer concrete. However, the precursor system of geopolymer concrete is known to be more heterogeneous compared to Ordinary Portland Cement (OPC) concrete, adversely affecting the data generated and the performance of the models. To its advantage, data enrichment through deep learning can effectively enhance the performance of prediction models. Therefore, this study investigates the capability of tabular generative adversarial networks (TGANs) to generate data on mixtures and compressive strength of geopolymer concrete. It assesses the impact of using synthetic data with various models, including tree-based, support vector machines, and neural networks. For this purpose, 930 instances with 11 variables were collected from the open literature. In particular, 10 variables including content of fly ash, slag, sodium silicate, sodium hydroxide, superplasticizer, fine aggregate, coarse aggregate, added water, curing temperature, and specimen age are considered as inputs, while compressive strength is the output of the models. A TGAN was employed to generate an additional 1000 data points based on the original dataset for training new predictive models. These models were evaluated on real data test sets and compared with models trained on the original data. The results indicate that the developed models significantly improve performance, particularly neural networks, followed by tree-based models and support vector machines. Moreover, data characteristics greatly influence model performance, both before and after data augmentation.

Established by the U.S. Green Building Council (USGBC), the Leadership in Energy and Environmental Design (LEED) became a sustainable leader of green building rating systems in American and many other countries. In Vietnam, LEED is expected as a potential solution in improving the sustainable quality of buildings for residents and solving the housing/infrastructure demand with a limit in resource consumption and minimizing negative environmental impacts. The study analyzed the awarded LEED 2009 credits by investigating the data of 36 of the total 42 LEED BC+D 2009 certified projects in Vietnam. The results of the investigation indicated the awarded credits were significantly implemented in Vietnam. These results were converted based on the summary updated on LEED version 4 of the USGBC report, to become a useful guideline for green building cost-efficiency strategies. Additionally, it also served as reference data for the Vietnamese public agency to update their green regulations based on the specific characteristics of Vietnam.

Sustainable construction addresses both rising housing demand and the need to reduce energy consumption, but is not yet widespread in Vietnam, although the number of Green Building Certified projects has increased significantly since 2015, especially those with LEED certification. Certification adds value to the project but also incurs additional costs and implementation challenges for general contractors (GCs) and other stakeholders. The growing popularity of LEED buildings requires GCs to understand their role in fulfilling the LEED requirements. We therefore conducted a thorough review of the previous research on LEED v4 guidelines and their local equivalents to determine what is expected of GCs working on LEED v4 BD + C projects in Vietnam. A survey of 72 experts, engineers, and architects working in the construction sector identified the LEED tasks where Vietnamese GCs lack experience and suggested solutions to address this shortfall were developed. In particular, Vietnamese GCs lacked experience in implementing their sustainable roles. These results provide a useful foundation for Vietnamese GCs seeking to expand the scope of their LEED work and identified necessary training. Our findings will also guide future research to help GCs in Vietnam adapt to LEED’s sustainability requirements and support sustainable construction in Vietnam.