During the second year of the Master in AI for Architecture & the Built Environment students have the opportunity of working hand in hand with a series of renowned experts and industry partners in various fields, to develop an in-depth individual research agenda. Students propose a thesis project, to be developed throughout the year, and are allocated with an Individual Thesis Advisor, Technical Advisor, Business Development and Industry Advisor. During the second year of the program, the curriculum of the program gives students the chance to either participate in an accelerator program or embark on a paid internship with renowned architectural and urban design offices around the world that collaborate with the programme. This experience enables students to apply their newfound expertise in real-world settings, contributing to impactful projects, establishing strong future career possibilities and expanding their professional networks.
A Computational Framework for Inferring Architectural Spatial Organization from Visual Input. Abstract: This thesis investigates whether Artificial Intelligence can infer a building’s internal spatial organization from its exterior image, using architectural typology as the mediating framework. Typology is treated here not as a stylistic category but as a relational, topological structure: a set of rules … Read more
Mapping out Spatial Intelligence Program: Master in AI for Architecture and the Built Environment (MaAI)Supervisor: Wassim Jabi Motion Pixels is a research project that explores how pedestrian movement can be transformed into spatial intelligence. By combining computer vision, trajectory analysis, behavioral mapping, and machine learning, the project converts video recordings of public spaces into spatial … Read more
A street-level method for predicting and explaining urban heat from surface composition and configuration
Abstract This project looks at turning waste cork materials into 3D printed acoustic panels, using design ideas taken from Gaudí’s work in the Sagrada Familia. The cork comes from reused bottle stoppers collected in Catalonia, then ground down and turned into a printable filament, so the whole process fits into a circular material workflow. On … Read more
PROBLEM: Current urban investment decisions, particularly in social housing, are largely based on financial feasibility studies, static socio-economic indicators, and ESG-style metrics that fail to capture how people actually experience and use space and often overlook real-time behavioral dynamics: how people move, engage with space, perceive safety, or interact socially. In dense metropolitan environments like … Read more
Abstract: Natural disasters, especially earthquakes, often leave roads blocked, buildings collapsed, and maps outdated, making navigation and response efforts highly challenging, That’s where we operate. Our project SeisNAV is an AI-powered platform that combines satellite imagery and computer vision to detect collapsed structures and road blockages, providing real-time mapping and navigation tools for disaster response … Read more
Abstract:Our research explores how data-driven digital tools can optimize emergency response times using geospatial analysis and computational simulation methods. Focusing on Kadikoy district in Istanbul, we simulated ambulance routes from stations to emergencies to emergency rooms, using distance as a proxy for response time. Our study analyzed two scenarios: i) the current infrastructure; ii) identifying … Read more
Abstract: In this class on Intelligent Prototyping within the MaAI program, we explored two distinct approaches to prototyping: 3D printing with robotic arms and real-time sensing with microcontrollers. Using parametric modeling tools, specifically Grasshopper, we designed and fabricated a series of 3D-printed clay pots. These included small, medium, and large-scale pots, with a focus on … Read more
Introduction:The AI Theory class has provided us with comprehensive foundation in artificial intelligence, covering both fundamental principles and advanced methods. Through topics such as clustering, neural networks, evolutionary computing, and decision-making models, the course aims to equip students with the theoretical knowledge and practical insights needed to apply AI across various fields, including disaster management … Read more
