Machine learning for architectural design: Practices and infrastructure

Tamke, Martin; Nicholas, Paul; Zwierzycki, Mateusz

doi:10.1177/1478077118778580

Cited by 56 publications

(42 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we review machine learning applications in three aspects (Table 2): (1) parametric design emulation, (2) generative design, and (3) design evaluation with supervised learning. ANN [15] Clustering [16] Design evaluation Plain ANN [17]- [19] ANN, PCA, SVM [20] Random Forest [21], [22] First, parametric design-applying machine learning models and blending statistical principles with computations-is a new approach that facilitates more variability in the design workflow. In the past decade, parametric design methods and tools were used in architectural and structural design for optimization purposes.…”

Section: Machine Learning For Building Designmentioning

confidence: 99%

“…However, the traditional parametric design requires setting the rules to be encoded in the program, and the exploration of the design space is still limited by the abilities of human designers. Machine learning techniques have been used to emulate the hard-coded rules and parameters, unveiling the underlying phenomena behind them [15], [23]. For example, a machine learning framework was designed by Yu Zhang et al to use principal component analysis (PCA) for interrogating, modifying, relating, transforming, and automatically generating design variables for the purpose of structural safety and daylighting environment optimization [21].…”

Section: Machine Learning For Building Designmentioning

confidence: 99%

See 1 more Smart Citation

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

229

View full text Add to dashboard Cite

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

show abstract

Section: Machine Learning For Building Designmentioning

confidence: 99%

Section: Machine Learning For Building Designmentioning

confidence: 99%

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

229

View full text Add to dashboard Cite

show abstract

“…AI has also made it possible to drastically optimize simulation durations to realtime simulations approximations, by projecting the results of previous simulation cases on new similar ones. This introduces a kind of "intuition for decision making" [18] for designers.…”

Section: Ai For Architectural Designmentioning

confidence: 99%

Will Artificial Intelligence (AI) Take over the Construction World? - A Multidisciplinary Exploration

Elhouar¹,

Hochscheid²,

Alzarrad³

et al. 2020

Proceedings of the Creative Construction E-Conference 2020

View full text Add to dashboard Cite

The late Stephen Hawking was reported to have said, "Computers will overtake humans with AI within the next 100 years. When that happens, we need to make sure the computers have goals aligned with ours." This statement is frightening to most, as very few people may like the idea of seeing computers take over the world. However, what can be more frightening is for those few people who like the idea to also make use of Hawking's suggestion and find a way to make sure the computers have goals that are strictly aligned with only theirs. There is a distinguishable apprehension among people of the role AI is set to play in the future of humanity, and this apprehension is transcending disciplinary boundaries. In the particular fields related to construction, there seems to be a genuine interest in integrating AI in each phase of a project to improve quality, enhance safety, and reduce costs, but this interest is countered by a legitimate concern that many types of jobs would be lost to AI-enhanced machines. In this paper, the authors tried to shed some light on how AI might change the face of the construction industry. The authors, spanning generations and disciplines in the industry, tried to answer the question "will AI take over the construction industry?" each from their own perspective including architectural, structural, and construction management. A synopsis of the status of the application of AI in construction and related fields is first provided, and then the authors offer their individual views with respect to how they expect AI to affect their side of the industry. This paper is an effort to gain insights into the perceptions of current and future construction related professionals of the role of AI and the impact it may have on the industry.

show abstract

“…New design tools, techniques and methodologies are being developed that are shifting the design processes from the individual to collaborative (Fok & Picon, 2016;Kocaturk, 2013;Kocatürk & Medjdoub, 2011), from disciplinary to interdisciplinary (Bhooshan, 2016;Hesselgren & Medjdoub, 2010;Sprecher & Ahrens, 2016), and from implicit to explicit (J. E. Harding & Shepherd, 2017;Jabi, Soe, Theobald, Aish, & Lannon, 2017;Oxman, 2006). The tools are becoming more adaptable (Burry, 2013), the processes are becoming more iterative and flexible (Imbert et al, 2012;Tamke & Thomsen, 2018;Wortmann & Tunçer, 2017), and the traditional form-based models are being abandoned in favour of data-rich and performative models (May, 2018;Mueller, 2011;Tamke, Nicholas, & Zwierzycki, 2018;Thomsen, Tamke, Gengnagel, Faircloth, & Scheurer, 2015). This rapidly changing situation in the architectural domain coincides with an increase in natural disasters (Snell, 2018), growing limitations of global resources (Mueller, 2011), climate change (Kwok, Kwok, Grondzik, Kwok, & Grondzik, 2018), and population growth (Carlile, 2014).…”

Section: Introductionmentioning

confidence: 99%

Smart processes for smart buildings: ‘sustainable processes’, ‘recyclable processes’ and ‘building seeds’ in parametric design

Haidar

Underwood

Coates

2019

Architectural Engineering and Design Management

View full text Add to dashboard Cite

The rapid evolution of digital technologies and the resulting emergence of novel design methodologies are coinciding with climate change, population growth and increased pressure on global resources. This concurrence evokes opportunities to harness the new design methods to develop smart design solutions and processes that respond effectively to sustainability requirements. Meanwhile, parametric design is emerging as an ideal design methodology to support sustainably in design, whereby the associative parameters in parametric design systems enable automation and synchronicity in generating design forms and evaluating these forms against their environmental performance. This research explores the multifaceted way in which parametric design supports sustainability, and how this can lead to a more holistic understanding of sustainability by shifting the focus from sustainable buildings to sustainable processes. In addition, the work shows how the reusability of parametric definitions in parametric design applications can enable designers to recycle the design process, where a parametric definition acts as a building seed that can be 'planted' in different projects to automatically generate different forms. This may enable practitioners from all over the world to collectively develop a 'seed library' that has the potential for architects to empower, automate and enhance the environmental values of their processes. To achieve this, the main changes and shifts in computational design are reviewed, together with the impact of parametric design and its related applications on the architectural design process. In addition, a case study is conducted to explore how parametric design can significantly accelerate processes in real practice, and how the overlooked potential of reusing parametric definitions can make distinctive results in real architectural projects. Finally, the efficiency of the seed library is discussed as opposed to the apparent issues such as validity of seeds, motivation for sharing, and copyright.

show abstract

Machine learning for architectural design: Practices and infrastructure

Cited by 56 publications

References 18 publications

State-of-the-art on research and applications of machine learning in the building life cycle

State-of-the-art on research and applications of machine learning in the building life cycle

Will Artificial Intelligence (AI) Take over the Construction World? - A Multidisciplinary Exploration

Smart processes for smart buildings: ‘sustainable processes’, ‘recyclable processes’ and ‘building seeds’ in parametric design

Contact Info

Product

Resources

About