The MaCAD is a unique online programme training a new generation of architects, engineers and designers ready to develop skills into the latest softwares, computational tools, BIM technologies and AI towards innovation for the Architecture, Engineering and Construction (AEC) industry.

GRAPH MACHINE LEARNING TOWARDS ADAPTIVE CITIES: A data-driven approach to sea level rise problematics

Abstract This thesis explores experimental approaches when addressing sea level rise challenges , the impacts of land loss due to sea rise and population growth. It delves into considerations associated with innovative approaches while emphasizing the integration of urban syntax and graph machine learning. Drawing upon case studies and open data, underscoring the importance of … Read more


Abstract This study delves into the innovative fusion of graph theory with architectural design and planning, facilitated by a structured BIM to Graph workflow. By conceptualizing architectural elements as nodes and their interconnections as edges within a graph, architects gain an adaptable and multifunctional tool for representation, analysis, and strategic planning. The graph’s inherent scalability … Read more

First step towards circular reconstruction. Damage assessment and material mapping of buildings in Ukraine through ground imagery processing.

An apartment building explodes after Russian army tank fire in Mariupol, Ukraine, March 11, 2022. (AP Photo/Evgeniy Maloletka)

Intro Russian full-scale invasion of Ukraine, which started on 24.02.2022, is the biggest war in Europe since WWII. It took the lives of dozens of thousands of Ukrainians a brought massive destruction [1] and ecological catastrophes. Some cities are completely erased. A massive piece of land is still occupied. This war and its consequences are … Read more

Superblock BCN

A Multidimensional Study of the Superilla My research starts from observing human behaviour. Often when we face a change in our lives, especially when it wasn’t planned, we feel resistance and it takes time before we accept and embrace it.  As you probably know Barcelona in the last few years lived some changes in its … Read more

Advanced Architectural Guide

Abstract Architecture enthusiasts face a dilemma when planning their travel visits. Either they spend a lot of time and effort researching and planning their routes, or they can rely on mainstream websites and blogs that tend to recommend well-known works, ruling out works with the same architectural interest that have received less media coverage. The … Read more


“Illuminating Spaces, Effortlessly!” I INTRODUCTION “This project utilizes graph machine learning to enhance architectural lighting design. Through GraphSAGE, we classify light sources considering their features and interconnections with architectural components, aiming to streamline the design process and consistently achieve optimal lighting scenarios.” I DESIGN PROCESS I DATA SET ZONES EDGES EDGES I MODEL DEVELOPMENT

Latent Studio

Explorer for new architectural dimensions Latent Studio is a groundbreaking web service that redefines initial-stage modeling for large architecture offices. It harnesses the prowess of 3D Generative Adversarial Networks (3DGANs) and a vast cloud-based voxel model database.This transformative process involves two crucial steps: data collection and training, culminating in a meticulously curated Typology Catalog. Along … Read more


Our project website can be accessed at Introduction Our research focused on hosting a machine learning model on the web that accesses Rhino.Compute. It receives an input of a polyline drawn on a Leaflet.js map by a user to indicate the central corridor spine of a building and returns a graph of that building … Read more


Harnessing the power of drone-based photogrammetry and artificial intelligence to create a low-cost urban wildfire diagnostic tool. In recent years, the global community has witnessed a significant upsurge in the frequency and intensity of wildfires. Driven by a combination of climate change, urban expansion, and land-use practices, these fires have not only devastated vast natural … Read more


Kala Academy Auditorium Refurbishment – Using Genetic Algorithms I PROBLEM STATEMENT I STATE OF THE ART EMPAC The interior was treated with various wall patterns applied to the walls leaving no flat surfaces to increase sound diffusion and decrease reverberation time, This made it rank as one of the most acoustically perfect concert halls in the … Read more

Skylight Performance

This project studies skylight performance in four given cities: Barcelona, Malina, Melbourne, and Vancouver collectively, by employing of Data-Encoding machine learning methods. ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- ——————————————————————————————————————————————————————————————————————————- Summary of Execution ‘Data_Encoding’ machine learning method offers renovative means for a variety of applications in architectural design. In order to have a … Read more

Facade Evolutions

By employing [input_output] + [pix2pix] combination of machine learning strategy, this exercise explores the opportunity to facilitate facade developments. [over 2000 variations] Inspirations [Input_Output] + [pix2pix] combination is a powerful machine learning tool for innovative architecture design. A meaningful and robust dataset is critical for a successful project. Pilot-test and extensive back-and-forth adjustments are also … Read more

Vastu in Graph Machine Learning

CONCEPT Vastu Shastra is a traditional Indian architectural science that provides a wide range of guidelines for design, layouts and construction of buildings. Vastu Shastra is based on the principles of ancient Indian texts and it aims to create harmonious and balanced living spaces that promote physical, mental and spiritual well being. WORKFLOW DESIGN PROCESS … Read more


A Graph Machine Learning Approach for Classifying Museums Layouts Based on their Circulation Patterns and Gallery Experiences. This project aims to use graph machine learning to evaluate and classify museum layouts and experiences. By leveraging the structure and relationships within a museum’s most contributing elements, such as galleries and circulation. The project aims to identify … Read more


Can we find a systemized approach for extracting the shape of cities? City.Style.GAN is a small research on the possible generative networks capables of generating new buildings massings according to the urban shape fo the city. Methodology: In a first aproximation to the urban generation, large portions of three urban tissues are extracted in OSMnx … Read more

ANNA, the avatar

Embracing artistic collaboration, Eugenia and Littieri created Anna, an AI Avatar. Images, text, sound, and voice converged, augmented by Melobites’ melodies. Albert Einstein’s voice was revived, while voice mod technology transformed singers’ voices. The harmonious fusion of art and technology captivated audiences. This project showcased the limitless potential of collaboration between human creativity and AI, … Read more

Wildlife Corridors

Our project focuses on modeling and predicting habitat fragmentation avoidance mechanisms using graphs. We investigate wildlife corridors in Australia, leveraging graph-based approaches to create coherent passages and connect forest areas. By analyzing satellite images, road data, and other metrics, we construct and evaluate graph models that incorporate forest containment, node characteristics, and connectivity. Our goal … Read more

Generative Urban Farming

The experiment parts from a self organizing model that iterates based in the incident sun hours, to later be evaluated in 2 methods: DCGAN’s and PIX2PIX. Problem Statement: The objective is to utilize urban farming strategically in central Budapest to enhance the affordability of student life. The key questions revolve around the potential yield, geometric … Read more


The project is intrigued by the comparison between human thinking and machine learning, particularly in understanding the distinctions between lived experience and acquired memory. To explore learned memory, we focus on Klara, an artificial friend from the book “Klara and the Sun.” Klara, a solar-powered robot, assists a sick child and possesses the ability to … Read more


RESEARCH QUESTION Custom facade design has high costs,currently these designs are reserved to high end residential design. What if AI could give a valid variety of proposals for balconies customized arrangements that take into account microclimate and privacy of the outdoor space? METHODOLOGY DESIGN PROCESS PIX TO PIX GAN Allows to explore several options It is quicker … Read more

ESTIMATE ESTATE – Discovering the Perfect Locale

With the recent upsurge in tourism worldwide, the Airbnb accommodation sector has become a thriving industry. As a result, the demand for Airbnb accommodations is poised for further growth, attracting an increasing number of individuals interested in entering this lucrative market. ●How can a new entrepreneur make a decision on the ideal location to open … Read more

Egress Prediction

This initiative is oriented towards the practical undertaking of identifying egress points within a floor plan. We have analyzed three typologies of a structure akin to multi-family dwellings or hotel-style establishments. After a thorough engagement with the process, there are subsequent measures to be considered, which we intend to elaborate upon in our final review. … Read more