NEW DIGITAL CRAFTSMANSHIP “DEEPSMART CORPUS”: LEARNING FROM PAVILION DATA WITH AN AI-ASSISTED MODEL

Date

2025-2-26

Author

Ayaz Erdağ, Ayça

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

176
views

0
downloads

Cite This

Architectural practice has undergone a profound transformation over the past two decades as digital technologies have reshaped design processes, tools, and material engagement. While these advancements have expanded architectural possibilities, they have also created a critical gap between architects and the production process. The relationship between design, materials and tools has weakened, often relegating architects to drafting instructions rather than engaging directly with construction. This dissertation presents the Architectural “DeepSmart Corpus”, a comprehensive framework designed to bridge this gap by integrating traditional craftsmanship with data-driven methodologies. By synthesizing historical knowledge, and data the DeepSmart Corpus empowers architects to create more precise, adaptable, and context-aware designs. Building on Deep Tech principles, the framework redefines the architect’s role by fostering seamless interaction between digital and physical realms. Pavilions serve as experimental case studies within this system, functioning as scalable environments for testing design strategies, data patterns, and construction techniques. Historically, pavilions have acted as critical pedagogical tools, reflecting technological and design innovations of their time. Through these pavilions, the DeepSmart Corpus extracts data and patterns from micro units to larger systems and this enhances both human and machine learning capabilities. By positioning architects as “extended craftsmen”, this hybrid framework enhances sensory and cognitive engagement, redefining architectural practice through the convergence of tradition and innovation. Ultimately, the DeepSmart Corpus establishes a transformative approach to architectural learning and production, ensuring that future designs remain resilient, data-informed, and seamlessly integrated across digital and physical realms.

Subject Keywords

Digital Craftsmanship, Data-Driven Design, DeepSmart Corpus, Architectural Innovation, Pavilions

URI

https://hdl.handle.net/11511/114490

Collections

Graduate School of Natural and Applied Sciences, Thesis