With the increasing number of disruptive events impacting the built environment, identifying and enhancing the resilience of building facades has become crucial. This study focuses on improving the resilience of building facades against seismic and thermal hazards using machine learning techniques. A comprehensive methodology is developed, integrating thermal and seismic resilience analyses within a unified framework. The study utilizes extensive simulations and machine learning models to predict resilience metrics, such as thermal autonomy and seismic drift angles, based on various building parameters. The approach enables architects and engineers to optimize building designs for enhanced resilience efficiently.
The research is specifically applied to low-cost housing in New Delhi, India, an area prone to both extreme weather and seismic activity. Detailed simulations are conducted using data on building materials, geometries, and environmental conditions. The results are used to develop predictive models that inform design improvements and resilience strategies. The study demonstrates significant improvements in the accuracy and efficiency of resilience assessments, providing actionable recommendations to enhance building performance. This integrated methodology offers substantial benefits for both academia and practice, paving the way for more resilient and sustainable building designs in vulnerable regions.
Keywords: Façade Resilience, Multi-hazard Approach, Unsupervised Machine learning, Supervised Machine learning, Prediction model, Quantitative Resilience Assessment, Resilience-based Design, Multi-attribute decision-making
... Read more

This paper explores the scope of using a deep learning framework for shape optimization of Catalan vaults for medium seismic areas. Catalan vaults are thin tile vaults that optimize the material usage of a floor slab without form-work and thus, additional material and labour. These structures can be constructed from tiles made from locally sourced earth which can provide an alternate to steel, timber, and concrete for areas with poor access to such materials, bringing down transportation, material, and carbon costs, providing opportunity to accommodate the consequences of rapid population growth. Seismic optimization of these vaults usually requires topology optimization and shape optimization tools. However, conventionally, these are computationally expensive and time-consuming - making them unsuitable for initial design explorations where a vast array of designs need to be quickly explored. As an alternative, a deep learning framework is explored as a design generation and optimization tool. This uses a Variational Autoencoder (VAE) trained on a dataset of 10,000 samples to extract novel meshes whose seismic performance is then predicted with the help of fully-connected dense Neural Network (NN) surrogate models trained on the results of a Linear Dynamic analysis in Karamba (in Grasshopper). An optimization loop is set-up through Gradient Descent Optimization where the gradient of the predicted score is minimized with respect to the latent space of the VAE - for single and multi-objective optimization. Conditioning the latent space of the VAE is further explored (Conditional VAE) so that the user is able to extract samples from the latent space with particular desirable characteristics such as a desirable height of the vault. This opens up opportunities to gain better control of the latent space and generate meaningful new samples that are able to incorporate user specifications. The geometry of the Catalan vault is represented in terms of polyedge force-densities that allow a 99.91% reduction in dimensionality and thus, faster convergence, as compared to other data structuring techniques explored in the literature as half-adjacency matrices. ... Read more

The Netherlands is facing the challenge of population growth and increasing diversity through migration, especially in larger cities like The Hague. These trends put pressure on the built environment and exacerbate social tensions. To address this, the thesis aims is to enhance spatial inclusion and social cohesion by densifying the built environment for the increasingly superdiverse population in the Haaglanden Region. Implementing the theories of an open and just city, as well as aligning this to the concept of space’s social logic and the 15-minute city is key to achieving this goal.

The region consists of many urban density types, each with different potentials for inclusive densification. The Mariahoeve neighbourhood, a typical postwar neighbourhood located on the outskirts of The Hague, offers many opportunities for inclusive densification. The strategies to be introduced for Mariahoeve are the introduction of courtyard typology buildings, a network of urban quality types, and main streets. The main streets expose the neighbourhood’s interiority through their enhanced permeability, and function as places of co-presence, raising awareness and affording interaction among different individuals. In a context of superdiversity, raising awareness through primary visibility is key in enhancing a sense of community.

The thesis concludes with a design proposal that strategically implements density to enhance connectivity, legibility, visibility, spatial diversity, and equity, to create an inclusively densified neighbourhood.
... Read more

This thesis explores the effects of patriarchy in the built environment and investigates solutions to gender inequality in the city. Although gender inequality has been fought against throughout the last century, women and men still do not enjoy equal social positions. One of the biggest manifestations is that of a difference in gender roles, wherein women are still expected to fulfil most - if not all - of the unpaid care labour in the family. The city fails to support activities connected to care labour, both in causing longer travelling times as well as failing to provide the building of community. Theoretical research on the topic of gender mainstreaming, supported by fieldwork in Vienna, a city that has been implementing these principles since the 1990’s, has provided an extensive overview of implementations that support gender equality in the city, which are combined in a pattern language.
The pattern language has been applied in a design for the exemplary location of Katendrecht, where they have been developed into a design for a gender equal neighbourhood. This project shows that design that offers diverse environments, facilitates community, increases the accessibility of public space and amenities, and prioritises slow and shared mobility results in a gender-equal city. ... Read more

This research investigates the assessment of thermal resilience in buildings with passive systems during heat waves using innovative computational methods. The study emphasizes the importance of resilient buildings in the face of rising temperatures and explores the concepts of thermal comfort and thermal resilience. A thorough review of existing methods and tools for evaluating thermal comfort and resilience is conducted.
The main objective is to develop a novel computational approach that integrates research findings to assess the thermal resilience of buildings during heatwave conditions. The approach incorporates two specific metrics: simplified metrics and Weighted Unmet Thermal Performance (WUMTP), which are modified to accurately assess thermal resilience in heatwave scenarios. The research also focuses on comparing the performance of these metrics and their effective utilization in assessing thermal resilience.
The computational methods are rigorously evaluated through simulations under controlled scenarios, accompanied by a comprehensive sensitivity analysis. This analysis explores the impact of modifying input parameters on the assessment of thermal resilience and provides insights into the factors influencing building resilience.
By incorporating sensitivity analysis, this research demonstrates the contributions of the developed computational methods, including the modified metrics, in enhancing our understanding of the relationship between design parameters, climatic conditions, and thermal resilience during heat waves.
This study aims to fill the research gap in thermal resilience and address the lack of assessment metrics and tools specifically tailored to heatwave scenarios. It offers valuable contributions to the academic community and practical insights for architects and engineers designing buildings resilient to rising temperatures and heat waves. The comparative analysis of the simplified metrics and WUMTP further enhances our understanding of their strengths and limitations in assessing thermal resilience. ... Read more

With the advent of Computer-Aided Design, the design and fabrication of complex free-form shells have become easier to achieve. However, this results in extensive usage of custom-made formworks for the production of shell components and falseworks which provide support for the shell during the construction process. Therefore, a modular design method is proposed for generating form-active spatial structures out of stackable blocks of a few types, having in mind its potential applications such as housing. Instead of shells, spatial masonry structures are thus the main consideration in the design process considering building on top of a vaulted ceiling. By designing a 3D interlocking grid and introducing a four-step topological design that is coupled with structural verification processes based on finite element modelling and discrete element modelling simulations, the geometry of interlocking stackable modular blocks can be automatically generated for constructing such spatial masonry structures. The proposed method ensures that the designed vaults are modular, reconfigurable, and self-supporting during construction, thus increasing the efficiency of mass production while allowing for combinatorial mass customization in designs. ... Read more