The process of architectural design aims at solving complex problems that have loosely defined formulations, no explicit basis for terminating the problem-solving activity, and where no ideal solution can be achieved. This means that design problems, as wicked problems, sit in a space between incompleteness and precision. Applying digital tools in general and artificial intelligence in particular to design problems will then mediate solution spaces between incompleteness and precision. In this paper, we present a study where we employed machine learning algorithms to generate conceptual architectural forms for site-specific regulations. We created an annotated dataset of single-family homes and used it to train a 3D Generative Adversarial Network that generated annotated point clouds complying with site constraints. Then, we presented the framework to 23 practitioners of architecture in an attempt to understand whether this framework could be a useful tool for early-stage design. We make a three-fold contribution: First, we share an annotated dataset of architecturally relevant 3D point clouds of single-family homes. Next, we present and share the code for a framework and the results from training the 3D generative neural network. Finally, we discuss machine learning and creative work, including how practitioners feel about the emergence of these tools as mediators between incompleteness and precision in architectural design.
10 October 2023 in Journal of Problem Based Learning in Higher Education
Students of art-based higher educational programs use artistic practices and academic methods to explore complex societal topics and produce artistic outcomes that embody new knowledge and insights. Universities have an essential role in helping to shape sustainable futures, and art-based research frequently explores complex and abstract topics, such as sustainability. In this paper, we provide reflections on 33 of the 127 undergraduate student projects we surveyed that concern sustainability over a period of 10 years at a problem-based learning (PBL) university as part of an Art and Technology degree program. Art and Technology is a STEAM education, where STEM (science, technology, engineering, and math) subjects are taught alongside artistic methods. Specifically, we investigate how students formulate sustainability problems within an art-based research framework by identifying the (1) themes within sustainability and art that were of most concern, (2) research aims of these projects within a PBL context, and (3) artistic and academic methods employed as part of the research process. Additionally, we provide select examples of the artistic outcomes of these student projects as evidence for how artistic methods and practices – by virtue of necessarily experiential work – can concretize the often abstract notion of sustainability, making it accessible to diverse student populations and the public.
7 February 2022 in International Journal of Architectural Computing
If we understand architecture as a three-part system formed by the building, its image, or drawings and images describing buildings, and the critical discourse around architecture, then the texts or ways of speaking about architecture play a key role in understanding the field and its development. By analysing a corpus of around 4.6 million words from texts written between 2005 and 2020 that form a part of critical discourse in computational architecture (understood as the result of the intense digitalization of the field), this paper aims to map ways of speaking about computational architecture. This contributes to architectural theory and might help gain a better understanding of the evolution of the digitalization of construction in general. Findings show that computational architecture is surrounded by a specific way of speaking, hybridized with words from fields such as biology, neuroscience, arts and humanities, and engineering. While some topics such as ‘sustainability’ or ‘biology’ come up consistently in the discourse, others, such as ‘people’ or ‘human’, have periods when they are more and less popular. After highlighting open research questions, the paper concludes by presenting a map of periodic and recurring topics in ways of speaking about computational architecture over the last 15 years, thus tracking and documenting long-term trends, and illuminating patterns in the broader field of digital construction.
ComPara is a corpus linguistics dataset in English focused on computational architecture or architecture where technology functions as a driver for its conceptualization, design, and materialization. Sometimes computational architecture is also referred to as digital, parametric, algorithmic or generative architecture, and, as has been shown, each of these terms has different flavours [9]. Other corpus linguistics for architecture have been built containing texts written over a relatively limited time span and focusing on the language used in the profession in general [1,2]. The text which makes up ComPara is written between 2005 and 2019 and focuses on computational architecture. The corpus is built from two sources: the journal Architectural Design [3] and the eVolo skyscraper competition [4]. The former is one of the journals which has focused most on the theoretical discourse surrounding computation in architecture [5], while the latter is one of the most prestigious competitions focusing on ‘technological advancements in architecture’ [4].