Skip to content

Automating building environmental assessment: A systematic review and future research directions

T.A.D.K. Jayasanka, Amos Darko, D.J. Edwards, Albert P.C. Chan, Farzad Jalaei, Automating building environmental assessment: A systematic review and future research directions, Environmental Impact Assessment Review, Volume 106, 2024, 107465, ISSN 0195-9255, https://doi.org/10.1016/j.eiar.2024.107465.

View Publication

Abstract

Building environmental assessment (BEA) is critical to improving sustainability. However, the BEA process is inefficient, costly, and often inaccurate. Because automation has the potential to enhance the efficiency and accuracy of the BEA process, studies have focused on automating BEA (ABEA). Updated until now, a comprehensive analysis of prevailing literature on ABEA remains absent. This study conducts the first comprehensive systematic analysis appraising the state-of-the-art of research on ABEA. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guided to systematically analyse 91 relevant studies. Results uncover that only 29.7% of BEA systems worldwide have automated their processes, with the US LEED residing at the vanguard of automation efforts. The New Buildings scheme was mostly focused on, while largely ignoring other schemes, e.g., Existing Buildings. Five key digital approaches to ABEA were revealed, namely building information modelling (BIM) and plug-in software, BIM-ontology, data mining and machine learning, cloud-BIM, and digital twin-based approaches. Based on identified gaps, future research directions are proposed, specifically: using data mining and machine learning models for ABEA; development of a holistic cloud-based approach for real-time BEA; and digital twin for dynamic BEA. This study generates a deeper understanding of ABEA and its theoretical implications, such as major constructs and emerging perspectives, constitute a basis for holistic, and innovation in, BEA.

Artificial Intelligence in Performance-Driven Design: Theories, Methods, and Tools

View Publication

Abstract

Artificial Intelligence in Performance-Driven Design: Theories, Methods, and Tools explores the application of artificial intelligence (AI), specifically machine learning (ML), for performance modeling within the built environment. This work establishes the theoretical foundations and methodological frameworks for utilizing AI/ML, with an emphasis on multi-scale modeling encompassing energy flows, environmental quality, and human systems.

The book examines relevant practices, case studies, and computational tools that harness AI's capabilities in modeling frameworks, enhancing the efficiency, accuracy, and integration of physics-based simulation, optimization, and automation processes. Furthermore, it highlights the integration of intelligent systems and digital twins throughout the lifecycle of the built environment, to enhance our understanding and management of these complex environments.

This book also:
• Incorporates emerging technologies into practical ideas to improve performance analysis and sustainable design
• Presents data-driven methodologies and technologies that seamlessly integrate into modeling and design platforms
• Shares valuable insights for developing decarbonization pathways in urban buildings
• Includes contributions from expert researchers and educators across a range of related fields

Artificial Intelligence in Performance-Driven Design is ideal for architects, engineers, planners, and researchers involved in sustainable design and the built environment. It’s also of interest to students of architecture, building science and technology, urban design and planning, environmental engineering, and computer science and engineering.

Causal effects of place, people, and process on rooftop solar adoption through Bayesian inference

Min, Y., & Ko, I. (2023). Causal effects of place, people, and process on rooftop solar adoption through Bayesian inference. Energy (Oxford), 285, 129510-. https://doi.org/10.1016/j.energy.2023.129510.

View Publication

Abstract

While previous studies have established correlations between rooftop solar adoption and various factors, a comprehensive understanding of the underlying causal mechanisms has been limited by the intricate interrelationships among these variables. To address this gap, we propose a Bayesian causal inference approach that examines the interplay of various factors influencing rooftop solar adoption across multiple cities. By employing post-phenomenology, we uncover latent variables encompassing place, people, and process, shedding light on how they shape public responses to emerging energy technologies. We analyze the causal effects of these factors and highlight the significance of housing and built environment attributes in determining energy expenditure and rooftop solar adoption, emphasizing the need for policies that target energy equity. Additionally, we reveal the influence of neighborhood spillovers on adoption, indicating the role of social norms and information diffusion. The observed city-level variability underscores the importance of local contexts and location-specific factors in the adoption process. Furthermore, we highlight the need to consider causal relationships and the indirect effects of people-related attributes mediated through place-related attributes. Overall, these findings contribute to a deeper understanding of the factors shaping rooftop solar adoption via causal modeling and underscore the importance of tailored policies to promote adoption.

Keywords

Spillover effects; Energy equity; Post-phenomenology; Ignorability; Factor analysis; Clean energy; Photovoltaic systems; Overcoming barriers; Technology adoption; Decision-making; Energy justice; United-States; Vulnerability; Diffusion; Deployment; Responses

Can ChatGPT Evaluate Plans?

Xinyu FuRuoniu Wang & Chaosu Li (2023). Can ChatGPT Evaluate Plans?, Journal of the American Planning Association, DOI: 10.1080/01944363.2023.2271893

View Publication

Abstract

Problem, research strategy, and findings
Large language models, such as ChatGPT, have recently risen to prominence in producing human-like conversation and assisting with various tasks, particularly for analyzing high-dimensional textual materials. Because planning researchers and practitioners often need to evaluate planning documents that are long and complex, a first-ever possible question has emerged: Can ChatGPT evaluate plans? In this study we addressed this question by leveraging ChatGPT to evaluate the quality of plans and compare the results with those conducted by human coders. Through the evaluation of 10 climate change plans, we discovered that ChatGPT’s evaluation results coincided reasonably well (with an average of 68%) with those from the traditional content analysis approach. We further scrutinized the differences by conducting a more in-depth analysis of the results from ChatGPT and manual evaluation to uncover what might have contributed to the variance in results. Our findings indicate that ChatGPT struggled to comprehend planning-specific jargon, yet it could reduce human errors by capturing details in complex planning documents. Finally, we provide insights into leveraging this cutting-edge technology in future planning research and practice.
Takeaway for practice
ChatGPT cannot be used to replace humans in plan quality evaluation yet. However, it is an effective tool to complement human coders to minimize human errors by identifying discrepancies and fact-checking machine-generated responses. ChatGPT generally cannot understand planning jargon, so planners wanting to use this tool should use extra caution when planning terminologies are present in their prompts. Creating effective prompts for ChatGPT is an iterative process that requires specific instructions.

Keywords

ChatGPT; large language model; natural language processing; plan evaluation; plan quality

Decoding the dynamics of BIM use practice in construction projects

Hu, Y., & Dossick, C. S. (2023). Decoding the dynamics of BIM use practice in construction projects. Construction Management and Economics, 1–25. https://doi.org/10.1080/01446193.2023.2277925

View Publication

Abstract

Over the past two decades, thought leaders positioned Building Information Modeling (BIM) as a driver to change the Architecture, Engineering, and Construction (AEC) industry. However, instances of unexpected BIM use have surfaced, with projects often shifting from BIM to hybrid or even solely 2D practices midway. What technology use conditions cause these practice-based rejections of BIM use and how these happen have not been fully explored and make BIM cannot fully play its role in a project. To fill this gap, we use structuration theory as a theoretical lens to analyze the interactions between BIM and project teams and explore how three technology use conditions, (interpretive, technological, and institutional), impact the interactions, which finally shape technology use practices. Specifically, a case study method has been selected. The research team attended a project for two years, collected meeting observations, and conducted surveys and interviews to track the emergent and situated BIM use practice in an integrated project setting with technology use conditions that changed over the course of the project. We analyzed how the three technology use conditions impacted the interactions between BIM and project teams in different ways and how these impacted change in different project phases. We conclude that the sustained use of BIM requires the alignment of project organizations with BIM features and alignment with both top-down and bottom-up investment in practice change, which includes motivation for senior management investment in a sustained project team, in individual capability training, and in early planning.

Keywords

Building information modeling; structuration theory; technology-in-practice; practice lens

Developing a multi-criteria prioritization tool to catalyze TOD on publicly owned land areas

Cai, M., Acolin, A., Moudon, A. V., & Shen, Q. (2023). Developing a multi-criteria prioritization tool to catalyze TOD on publicly owned land areas. Cities, 143, 104606-. https://doi.org/10.1016/j.cities.2023.104606

View Publication

Abstract

Public agencies can take a leading role in catalyzing TOD by making land available to developers (selling or leasing land, potentially below market prices). In particular, park-and-ride areas that are publicly owned can be leveraged to support TOD uses, such as affordable housing, office space, small businesses, and mixed-use buildings given their convenient access to transit systems and often large land areas. However, few previous studies have discussed the use of publicly owned park-and-rides, which are an important component of publicly owned land, as a catalyst for TOD. To fill the gap in the literature and effectively support TOD planning, this research developed a multi-criteria prioritization tool to identify the most promising locations for TOD and tested it at three park-and-ride sites owned by the Washington State Department of Transportation. The tool was developed through the Delphi process, which is an effective and inexpensive approach to evaluate relevant indicators by synthesizing the opinions of experts from various backgrounds. Five categories with a total of 14 TOD indicators, including transit supportive land-use zoning, job accessibility, land price, land-use mix, and household income, were selected as measures of TOD suitability. The importance of these indicators varied with three different TOD scenarios: (1) emphasis on affordable housing, (2) emphasis on market-rate housing, and (3) emphasis on mixed-use development. Using the calculated suitability scores, this tool can prioritize potential TOD sites for further review.

Keywords

TOD; Delphi method; Multi-criteria planning tool; Multi-sources geospatial data; Publicly owned land

Population Health Initiative awards 2 Climate Change Pilot Grants to CBE Researchers

Population Health Initiative awarded a Climate Change Pilot Grant to two teams that includes CBE researchers. Projects will begin January 2024, and were awarded $50,000. Read the full story here. Project title: “Sustainable metamaterials for insulation applications.”  Project team: Eleftheria Roumeli, Materials Science & Engineering Tomás Méndez Echenagucia, Architecture Project abstract: Amidst an urgent global shift towards a circular economy, the demand for sustainable materials has reached a critical juncture. This transformation requires materials sourced from renewable sources, processed via…

Kevin Muiruri

Research interests: project delivery methods and impact to project success; project control and construction contracts; privatization in construction and private-public partnerships; project cost management; sustainability.

M.S. Construction Management, University of Washington (2022)
B.S. Civil Engineering, Dedan Kimathi University of Technology, Kenya (2017)

Industry-Faculty-Student collaboration through the Applied Research Consortium

Owner of RDF Consulting Services and consultant for Turner Construction, Renzo di Furia, is working with Associate Dean for Research Carrie Sturts Dossick in supporting student-industry collaboration. “Applied Research Consortium brings together an interdisciplinary group of built environment firms with faculty experts and graduate student researchers at the University of Washington’s College of Built Environments (CBE) to address the most vexing challenges that firms face today.” A case study in applied research is highlighted in the article. 3D modeling was…

Blockchain-Enabled Supply Chain Coordination for Off-Site Construction Using Bayesian Theory for Plan Reliability

Kim, M., Zhao, X., Kim, Y.-W., & Rhee, B.-D. (2023). Blockchain-enabled supply chain coordination for off-site construction using Bayesian theory for plan reliability. Automation in Construction, 155, 105061–. https://doi.org/10.1016/j.autcon.2023.105061

View Publication

Abstract

The potential of blockchain is being widely explored within the construction industry, particularly for transparent communication and information sharing. However, only limited research has focused on implementing blockchain to address the challenge of aligning conflicting interests among independent agents, specifically, supply chain coordination. This paper develops a blockchain-enabled supply chain coordination system that facilitates the alignment of diverse decisions made by stakeholders in an off-site construction supply chain. To achieve this goal, Bayesian updating is employed to estimate the probabilistic distribution of plan reliability, enabling the calculation of a supplier rebate that incentivizes the contractor to schedule deliveries aimed at minimizing joint supply chain costs. Additionally, the paper describes a blockchain-enabled system that allows practitioners to measure plan reliability. The research findings demonstrate that the blockchain-enabled supply chain coordination system fosters shared common knowledge among project stakeholders and facilitates real-time updates of changes in the contractor's plan reliability, aligning the interests of both the supplier and contractor.

Keywords

Supply chain coordination; Bayesian updating; Plan reliability; Rebate pricing; Blockchain; Smart contracts; Off-site construction