The course informs the students about the constantly evolving technological landscape and provide them with the instruments allowing one to evaluate different technologies and apply them to solve the problems within the industry. Moreover, this course gives a broader perspective on data and machine learning pipelines enabling the students to interact with data specialists using correct terminology and understanding the implications of project decisions.
The existing challenges in the construction industry require its actors to undergo a rapid digitalization. Together with sustainable development digital transformation and technological literacy are among the aspects considered as the most important bottlenecks in the architectural branch.
The aim of this course is to inform the students about the constantly evolving technological landscape and provide them with the instruments allowing them to evaluate different technologies and apply them to solve problems within the industry. Moreover, this course gives a broader perspective on data and machine learning pipelines enabling the students to interact with data specialists using correct terminology and understanding the implications of project decisions.
During the course, the students would get a general overview of machine learning algorithms and their application in the architectural industry, learn to evaluate the pros and cons of different algorithms according to the use case, and eventually apply these techniques in a POC-form.
The seminar is intended as a resource for the main studio project but is not connected to the studio’s topic. The students are encouraged to use the materials and skills acquired during the seminar in their studio work.
At course completion the student will:
(PaintDumpster/environmental_data_workshop at ndvi) – Link to GitHub This project aims to detect and classify different types of greenery in satellite imagery by utilizing color and edge detection techniques. The study area is located in Barcelona, Spain (41.396536, 2.194554). The stable version employs color and edge detection for image segmentation, while an alternative method integrates LiDAR … Read more
This project focuses on Evia, Greece, where devastating wildfires in the summers of 2021 and 2023 caused massive environmental damage. This is only an example, but this pipeline could be applied to any wild-fire affected area. Our aim is to quantify green loss and monitor post-fire ecosystem recovery. Thus we compare satellite imagery from key … Read more
The project is situated in Athens, Greece, which overheats in the summer. We wanted to test a hypothesis: The overheating is the result of too much hardscaping (asphalt, concrete, brick) and not enough greenery. We wanted to compare the NDVI (a measure of greenery in a city) taken from Satellite images to Land Surface Temperature … Read more
The goal of this project is to compare between the economic stability of an agriculture first city. Hamburg’s agricultural wealth is largely connected to its surrounding regions—particularly Schleswig-Holstein and Lower Saxony, which are among Germany’s leading food producers. Consequently, we focused on peripheral areas of the city that have recently transitioned into agricultural land, allowing … Read more
Can an AI agent learn how to carve a shape — not by following a predefined path, but by figuring it out on its own? https://github.com/IaaC/AI_Robotics_Octopus.git Inspired by the precision of traditional craftsmanship, especially techniques like Japanese joinery where every cut matters, we wanted to see if a machine could learn that same logic in … Read more
