Starting point: 

How can computational methods, machine learning, and artificial intelligence be used to enhance sustainability outcomes and optimise value creation in the Architecture, Engineering, and Construction (AEC) sector?

This topic may include consideration of: computational methods, machine learning, and artificial intelligence insights to help the AEC sector overcome challenges that consider key decision factors around resource use, carbon emissions, waste production, project timelines, project budgets, and project benefits; how manufacturing information databases and systems can be leveraged to inform decision-making across key aspects of sustainable built assets. 

Project Summary: 

Research Problem 

In mega-projects, (i) 86% of budget forecast are exceeded (Flyvbjerg et al., 2002); (ii) 70% of all project deadlines are not met (Ryan and Duffield, 2017); and (iii) only 0.5% of the benefits promised are realised (Terrill et al., 2020). These numbers are a damning indictment of current AEC firms and can stem from inefficient processes. The silver lining is the prospective capacity of improving these numbers through process optimisation (PO), hence increased efficiencies (Pan and Zhang, 2021; Castro-Lacouture, 2009). 

Research Aims, Objectives & Questions 

“Exploration of the usage dimensions of digital process optimisation in AEC sector”, is the main aim of this research.  

Methodologies 

Design Science Research (DSR) will be the core of this research. DSR is a problem-solving paradigm which tries to contribute to the body of knowledge through creating innovative “artefacts” (vom Brocke et al., 2020; Hevner et al., 2004). Let us answer the DSR’s three main questions, as regards this research: 

1. Q: What is the purpose of the artefact? 
   A: Discover bottlenecks and repetitive cycles within AEC firms’ digital business processes, then: 

1. Management level: suggest tailored optimised version of those processes. 

2. User level: suggest tailored automation solutions, to skip the required steps for completion. 

2. Q: What will be the output artefact? 

1. Process Mining: Discover, monitor, and curate the business processes within an AEC firm through process mining. 

2. Process Optimisation: An optimised, re-engineered version of a process cycle will be suggested to the user. 

3. Process-Automation recommender system: Through process analysis, repetitive and duplicate process cycles are detected, and a corresponding automation action is suggested to the user. 

3. Q: How the artefact will be evaluated? 

1. Quantitative – Mathematical: Through ML measures, the performance will be checked to be close enough to that of a human doing the same task. 

2. Qualitative – Domain-Knowledge: Through interviews with stakeholders, after using the artefact in their firm, the success of the artefact can be evaluated based on its real-world utility and usefulness. 

Expected Outcomes 

The expected implications of this research could be: 

• Digital software processes (aka tasks) can be finished faster, hence (i) more efficiency, (ii) reduced workforce, (iii) more time for quality assurance. 

• Help the AEC sector’s digital transformation through innovative SOTA AI. 

References 

1. Flyvbjerg, M. S. Holm, and S. Buhl. Underestimating costs in public works projects: Error or lie? Journal of the American Planning Association, 68(3):279–295, 2002. doi:10.1080/01944360208976273. 

2. Ryan and C. F. Duffield. Contractor performance on mega projects – avoiding the pitfalls. In A. Mahalingam, editor, Working Paper Series, Proceedings of the EPOC-MW Conference, pages 1–34, Stanford Sierra Camp, California, US, 2017. Engineering Project Organization Society. URL https://hdl.handle.net/11343/168246. 

3. M. Terrill, O. Emslie, G. Moran, and i. b. Grattan Institute. The rise of megaprojects: counting the costs. Technical report, 2020. URL http://nla.gov.au/nla.obj-2991088280. 

4. N. Nalgozhina and R. Uskenbayeva. Automating hybrid business processes with rpa: optimizing warehouse management. Procedia Computer Science, 231:391–396, 2024. ISSN 1877-0509. doi:https://doi.org/10.1016/j.procs.2023.12.223. URL https://www.sciencedirect.com/science/article/pii/S1877050923022354. 14th International Conference on Emerging Ubiquitous Systems and Pervasive Networks / 13th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (EUSPN/ICTH 2023). 

5. Y. Pan and L. Zhang. Automated process discovery from event logs in bim construction projects. Automation in Construction, 127:103713, 2021. ISSN 0926-5805. doi:https://doi.org/10.1016/j.autcon.2021.103713. 

6. J. vom Brocke, A. Hevner, and A. Maedche. Introduction to design science research. pages 1–13, 2020. doi:10.1007/978-3-030-46781-4_1.