Monday, 20.04.2026, 15:15 via Zoom

Spatial Data Representation

Architectural and urban spatial data are conventionally represented through geometry—coordinates, dimensions, and visual fidelity. Yet, when the objective shifts from drawing space to reasoning about it, geometry becomes secondary to topology, where relationships, adjacency, connectivity, and circulation patterns hold the primary semantic meaning. This talk introduces a data modeling perspective for spatial datasets, employing graph and image representations and corresponding machine learning models to process them.

Seyran Khademi is a Senior Assistant Professor at the Faculty of Architecture and the Built Environment (ABE) at TU Delft, where she co-directs the AiDAPT Lab. She works at the intersection of artificial intelligence and computer vision, with a focus on data-driven methods for analyzing and generating spatial and visual data such as floorplans, urban environments, and architectural imagery. She is involved in initiatives such as the Data Refinery Lab and develops educational programs including the “AI in Architecture” course on edX. She is also the creator of the AIBlocks YouTube channel, where she shares research and discussions on AI and design.Seyran received her PhD from TU Delft in 2015 in statistical signal processing and optimization, followed by postdoctoral research in intelligent audio and speech systems and computer vision. In 2020, she was a research-in-residence fellow at the Royal Library of the Netherlands, working on visual recognition for children’s book collections.