Sustainable Artificial Intelligence: Digital Twin in ACE (Architecture, Construction, Engineering) Project Management

This paper evaluates the impact and application of sustainable artificial intelligence (AI) and digital twin (DT) on architecture, construction, and engineering (ACE) project management. The paper addresses the following research question: How can sustainable AI and DT improve the performance and sustainability of ACE projects? The paper follows a four-step methodology: (۱) data collection; (۲) data analysis; (۳) application of sustainable AI and DT to a case study; and (۴) evaluation of the impact and application of sustainable AI and DT. The paper presents and discusses the findings from the data analysis and the case study, and compares and contrasts them with the existing literature and practices. The paper finds that sustainable AI and DT can significantly improve the performance and sustainability of ACE projects, by providing intelligent and innovative solutions that address the challenges and opportunities of the ACE sector. The paper also identifies some challenges and limitations that need to be addressed and overcome, such as data quality and security, system interoperability and integration, user acceptance and trust, ethical and legal issues, and social and environmental justice. The paper contributes to the literature on the use of AI and DT in ACE project management, and the challenges and opportunities for sustainability, by providing a comprehensive overview of the existing research, a database and dashboard of the ACE project information and data, and a set of patterns and insights derived from the data and the case study. The paper also contributes to the practice of sustainable AI and DT in ACE project management, by demonstrating how they can be applied to a specific ACE project or case study, and by assessing their impact and application on the project performance and sustainability.

کلیدواژه ها:

sustainable AI ، digital twin ، ACE project management ، performance ، sustainability