Dr. Abdulrahman Alymani, Assistant Professor of Architectural Engineering at Alfaisal University, co-organized a workshop titled, “Exploring Building Topology Through Graph Machine Learning” in the Association for Computer Aided Design in Architecture (ACADIA) conference in collaboration with Dr. David Andres Leon for the Institute for Advanced Architecture of Catalonia and Dr. Wassim Jabi, Selda Pourali Behzad and Michelle Salamoun from Cardiff University. The workshop was held on October 21, 2023 in the ACADIA 2023 conference. ACADIA is an international network of digital design researchers and professionals, which facilitates critical investigations into the role of computation in architecture, planning, and building science, encouraging innovation in design creativity, sustainability, and education.
The workshop focused on graph machine learning. Graph theory offers a powerful method for analyzing complex networks and relationships. When combined with machine learning, graph theory can provide valuable insights into the data generated by 3D models. The workshop integrated advanced spatial modeling and analysis and artificial intelligence, highlighting the importance of technological advancements in shaping the future of architecture and design. It introduced participants to novel workflows that link parametric 3D modeling with concepts of topology, graph theory, and graph machine learning. The workshop leads used TopologicPy, an advanced spatial modeling and analysis software library designed for Architecture, Engineering, and Construction, paired with DGL, a powerful machine learning library that provides tools for implementing and optimizing graph neural networks. In essence, this process blends cutting-edge technologies and architectural principles that will shape the future of design. Participants learned how to use these workflows to convert 3D models into graphs, analyze their properties, and perform classification and regression tasks. Participants in the workshop also learned how to create synthetic datasets based on generative and parametric workflows and build and optimize graph neural networks for specific tasks.
The workshop is an activity under the umbrella of the Computational Methods and Intelligent Technology in Architecture and Design (CM-iTAD) Lab. The Director of the CM-iTAD lab is Dr. Abdulrahman Alymani in which he focuses on addressing the need for a creative workflow using digital fabrication, simulation software, artificial intelligence, and the ability to design custom software development tools to solve unique architectural design problems. Multidisciplinary approaches will enable the architecture discipline to discover innovative computational methods for use in creative and design work. Lab activities include parametric and generative form-finding, preparing digital information for rigorous analysis, and integrating the logic of digital fabrication into design processes. The lab will integrate architecture, computer science, and engineering, contributing to an interdisciplinary design approach.
