| id |
acadia23_v2_408 |
| authors |
C Kim, Frederick; Johanes, Mikhael; Huang, Jeffrey |
| year |
2023 |
| title |
Flow2Form: A Flow-Driven Computational Framework for Early Stage Architectural Design |
| source |
ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 408-418. |
| summary |
Flows have been a persistent theme as a rational and formal basis for architecture. This paper introduces a flow-based design framework for architecture using parametric modeling and machine learning analysis. It explores the integration of flows’ rational and figurative aspects into the early stages of the design process. The research employs para- metric tools and machine learning algorithms to represent and analyze flows, focusing on the artisanal and craft processes aiming for circular proto-typology as a transfor- mative architecture. The framework involves three stages: 3D flow modeling, machine learning analysis of formal and topological properties, and process-based programming and optimization. The results include volumetric representations of 16 artisanal flows and the classification of nodes based on their formal and topological characteristics. The framework enables the exploration of flow-driven architectural design, and bridges the gap between human interpretation and computational design. The research contributes to understanding flows to form in architecture, and the potential of machine learning in shaping architectural space. |
| series |
ACADIA |
| type |
paper |
| email |
|
| full text |
 file.pdf (2,450,906 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2024/12/20 09:12 |
|
