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.

Ark{Check} – A Machine Learning Approach to Architectural Documentation Review

Abstract Architectural drawings and construction documentation are critical in the construction industry, serving as the main means of communication between different disciplines and acts as a blueprint on guiding the construction of the built environment. However, errors in these drawings are quite common and often leads to significant delays, cost overruns, and structural issues. This … Read more

Predictive Analytics in Urban Development: Assessing Real Estate Viability with AI

INTRODUCTION The development of smart cities has become an integral part of modern urban planning as a result of rapid urbanization and technological advances. This thesis examines the rapidly growing field of artificial intelligence (AI) as well as how it can revolutionize urban analysis across a wide variety of industries. In particular, I will focus … Read more

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

Spatial.Revelations

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

OptiLight

“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. With the use of a Generative Adversarial Network (3DGAN) and a vast database of voxelized architectural massings, the end resultis an infinite typologies catalogue of intermediate shapes and scapes to explore. Along all steps (dataset, … Read more

WEB GRAPH MACHINE LEARNING

Our project website can be accessed at bit.ly/graphml 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

FireFly

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

SOUND INTELLIGENCE

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