Machine learning in the discipline of architecture: A review on the research trends between 2014 and 2020

Abstract

Through the recent technological developments within the fourth industrial revolution, artificial intelligence (AI) studies have had a huge impact on various disciplines such as social sciences, information communication technologies (ICTs), architecture, engineering, and construction (AEC). Regarding decision-making and forecasting systems in particular, AI and machine learning (ML) technologies have provided an opportunity to improve the mutual relationships between machines and humans. When the connection between ML and architecture is considered, it is possible to claim that there is no parallel acceleration as in other disciplines. In this study, and considering the latest breakthroughs, we focus on revealing what ML and architecture have in common. Our focal point is to reveal common points by classifying and analyzing current literature through describing the potential of ML in architecture. Studies conducted using ML techniques and subsets of AI technologies were used in this paper, and the resulting data were interpreted using the bibliometric analysis method. In order to discuss the state-of-the-art research articles which have been published between 2014 and 2020, main subjects, subsets, and keywords were refined through the search engines. The statistical figures were demonstrated as huge datasets, and the results were clearly delineated through Sankey diagrams. Thanks to bibliometric analyses of the current literature of WOS (Web of Science), CUMINCAD (Cumulative Index about publications in Computer Aided Architectural Design supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD, and CAAD futures), predictable data have been presented allowing recommendations for possible future studies for researchers.

Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges

“…Communication is pivotal in architectural design, especially when conveying concepts to clients or team members (Özerol and Arslan Selçuk, 2023;Furmanek, 2021). ChatGPT aids in creating design documentation by generating clear explanations of design decisions and features (Mykoniatis et al, 2013;Baduge et al, 2022).…”

“…Exploring collaborative frameworks where AI becomes an integral part of the design team prompts reflection on the evolving role of architects in this AI-infused landscape (Lin and Xu, 2022;Jaruga-Rozdolska, 2022;Peng and Ye, 2022;Baduge et al, 2022;Basarir, 2022;Seo et al, 2020). The communication and visualization of architectural ideas profoundly impact design discourse (Mykoniatis et al, 2013;Özerol and Arslan Selçuk, 2023;Yang, 2022). Generative AI tools, with their capacity to interpret and generate visual content, have the potential to revolutionize representation and visualization in architectural design (Pena et al, 2021;Chen, 2021;Cantarelli et al, 2018;Furmanek, 2021).…”

Deep Learning for Earthquake Disaster Assessment: Objects, Data, Models, Stages, Challenges, and Opportunities

“…(1) This type of data can reflect disaster situations in near real time, which can help disaster response teams have more comprehensive information when making relevant decisions. (2) Collecting this kind of data makes it possible to obtain help messages in time and coordinate relevant resources to carry out the emergency rescue. (3) Rescue teams can not only learn about the situation in the disaster area from social media information but also be able to monitor the situation of some rumours in time to avoid further panic.…”

“…DL, a significant branch of machine learning (ML), has become an essential research topic in artificial intelligence (AI) with the advent of big data. The concept of DL originated from the study of artificial neural networks (ANNs) and consists of multi-layer ANNs covering the supervised and unsupervised learning parts of the ML [2]. Its purpose is to find specific rules from large sets of sample data and use these rules to analyse target samples.…”

Artificial Intelligence-Powered Computational Strategies in Selecting and Augmenting Data for Early Design of Tall Buildings with Outer Diagrids

“…Creative exploration through machine learning (ML), particularly for predicting structural performance, becomes possible nowadays as computational tools are offered to navigate this challenge. ML, especially, is seen as holding the promise of revolutionizing architectural design by predicting structural outcomes even before construction begins [5], thanks to the exploration of a number of possibilities far beyond human inspection. While the full potential of data-centric design has yet to be realized on a global scale, its possibilities are considered vast.…”