Urbanization and climate change have intensified urban heat island effects, significantly affecting outdoor thermal comfort (OTC) in cities. Traditional methods of assessing the influence of urban environments on OTC often rely heavily on computational simulations, neglecting the integration of user-centric data and comprehensive environmental monitoring. This research addresses the critical gap by employing a multi-domain, mixed-method approach to evaluate the influence of building facades on outdoor thermal comfort, specifically in the Acquabella district of Milan. To address the gap, this study suggests a structured workflow beginning with a participatory workshop and a long-term survey to gather demographic data and user perceptions, identifying areas of significant thermal discomfort. These insights inform the simulations conducted using ENVI-met software, which model the Physiological Equivalent Temperature (PET) across different facade geometries and material properties. Real-time validation is achieved through a thermal walk, which includes field measurements and on-site evaluations to capture situational thermal perceptions. The research findings underscore the substantial impact of facade materiality on thermal perception. The study also reveals that aesthetic preferences and psychological factors play a crucial role in thermal perception, highlighting the necessity of integrating these aspects into urban design strategies. These findings are synthesized into a decision matrix that guides the design of retrofit strategies. Proposed solutions focus on modifying facade materials, increasing vegetation, and optimizing the built environment based on user feedback. Simulations of these design proposals using ENVI-met demonstrate significant improvements in thermal comfort, validating the effectiveness of the proposed interventions. This thesis presents a comprehensive framework for assessing the multi-domain influence of facades on outdoor thermal comfort, advocating for the integration of user-centric data and participatory approaches in urban design. The methodology and findings offer valuable insights for policymakers, urban planners, and researchers aiming to enhance urban thermal environments and address the challenges posed by climate change and urbanization.

The growing threat of climate change highlights the necessity for long-term solutions in the construction industry. Buildings account for a large share of worldwide energy consumption and carbon dioxide emissions, so there is an urgent need for creative techniques to improve energy efficiency and reduce their ecological footprint. This thesis focuses on this by creating a computational optimization workflow for incorporating hempcrete, a low-carbon construction material, into high-performance structures during the initial stages of design. This approach uses a multi-objective optimization process to offer optimal solutions adapted to various climates and building types, optimizing energy efficiency and daylight while limiting global warming potential. Architects and engineers can get greater performance and sustainability results by experimenting with different layout options and design parameters using parametric modelling, energy analysis, and optimization algorithms. The suggested workflow provides a systematic technique to facilitate decision-making during the key design steps, promoting hempcrete implementation and accelerating the shift to performance-driven architectural design in response to climate change problems.

In response to the European Commission's 2020 Renovation Wave strategy aiming to double the annual rate of energy renovation for buildings by 2030, this thesis addresses the challenge of optimizing retrofitting planning using planning optimization algorithms. Despite the economic and practical hurdles identified in existing research, limited attention has been given to optimizing the timing and sequence of retrofitting actions. Recognizing the complexity introduced by uncertainty factors such as material degradation rates,this study draws parallels between retrofitting and predictive maintenance problems. This thesis is divided into two main sections: the first establishes the theoretical foundation, covering retrofitting principles, Markov Decision Processes, and planning algorithms like Q-learning and Value Iteration; the second applies these theories to practical implementation to develop a methodology for retrofitting planning optimization. Detailed methodologies are discussed, emphasizing building energy performance and degradation factors, with conclusions drawn to inform the simulation of building performance over time. This comprehensive approach aims to advance the current understanding and application of planning optimization in the building retrofitting domain.

Across the world, countries are facing housing shortages and the Netherlands is no different. The increasing demand for new housing exceeds the growth rate of the architecture, engineering, and construction industry. Current solutions remain small in scale and therefore unsustainable. Multi-family housing is the optimal typology to address the housing shortage but the industry cannot design and build these projects fast enough. Automation can help. In 2016, Kevin Kelly[2016] reframed the conversation about automation, by stating "our most important mechanical inventions are not machines that do what humans do better, but machines that can do things we can't do at all." Humans cannot address the housing crisis alone, but automation through the application of deep learning models can bring well-designed spaces to everyone.

Since the introduction of computers, architects have looked for ways to automate menial tasks. Some researchers even imagine a future where the machine becomes a partner to architects and designers, contributing to the design process. This ambition requires that the algorithms train themselves. Innovations in the field of deep learning have made this possible by allowing algorithms to train themselves through the use of artificial neural networks. When it comes to applying deep learning to generative design tasks, however, there is little research. The studies that have been done generate geometry that is small in size (64 x 64 x 64 voxels) and focuses on objects like chairs, not on buildings. 3D generative adversarial networks show promise for generating building geometry. By automating design, it is possible to apply expert knowledge on good design to all projects so everyone has access to well-designed buildings.

This research aims to develop the architecture for a generative adversarial network that produces feasible building geometry. An important first step was identifying and pre-processing a data set that could be used for this purpose. The data set is released with the publication of this thesis so it can be used for further research. Through this thesis, the Improved 3D Wasserstein Generative Adversarial Network architecture has also been developed and documented. The research found that using a combination of Wasserstein loss with gradient penalty, Leaky ReLU activation functions in the generator and the critic, and the RMS Prop optimizer results in an architecture with stable training and outputs that are similar in size, shape, and proportion to the training data with minimal noise in the output. Performance of 3D Wasserstein generative adversarial networks with these hyperparameters was improved even further when using ten layers and a larger number of channels. The experiments concluded that generative adversarial networks can be used to generate building geometry and can be an area of continued research to improve generative design tools and support the automation of architectural design.

Current building operations can be improved through smart predictive operation based on weather and use patterns in order to save energy with minimal impact on the building fabric and daily use. The existing literature has investigated implementations, and potential savings through combining with variable tariffs, however, this thesis addresses the issue of how different buildings differ in their suitability for such smart control.

In this thesis, a digital twin of a school is created and adjusted to test differences in building fabric factors. These are combined with multiple Deep Reinforcement Learning (DRL) agents, which are trained to operate the schools more efficiently by controlling the heating set-point as well as natural ventilation of the buildings in order to save energy while maintaining comfort. The DRL agents vary in their ability to observe future weather as well as their internal network model architecture.

The results show a high energy saving compared to a simple baseline, despite the few building controls available to the agents. In addition, some algorithms out-compete even rule-based controllers, which were tested as a stricter baseline. The results also confirm a theory revealed through the literature review, that buildings with higher energy input, storage and control have a larger potential for energy savings. Additionally, the types of DRL models used also greatly influences the agents’ ability to perform well, and generally more advanced models performed better. The findings can be used to access a building’s suitability for and potential benefits from such predictive smart control.

The Netherlands aims to reduce greenhouse gas emissions by 49% before 2030, with the built environment contributing 15% of these emissions largely due to the heavy reliance on natural gas to meet space heating demands. To phase out natural gas, alternatives such as heat pumps and district heat networks are being considered. However, adapting existing buildings to lower supply temperature district heating requires effective refurbishment to maintain thermal comfort for occupants. The challenges hindering this process include i) addressing multiple housing typologies at the neighbourhood scale, ii) complexity of evaluating refurbishment measures by decision-makers, iii) uncertainty due to lack of consideration of life cycle costs and occupancy behaviour pre and post-refurbishment leading to performance gaps in energy savings and iv) current computationally demanding and inaccessible tools to assess refurbishment measures. Therefore, this thesis proposes a method to develop a surrogate model-based decision-making tool that can help homeowners efficiently assess optimal, combined refurbishment measures to help homeowners transition to low-temperature district heating. In order to develop this tool, the study examines literature studies that help define the input parameters for the underlying parametric simulation including. This also helped define the key performance indicators including energy savings, hours too cold and global cost. Furthermore, the underlying simulation model with 13 input parameters provides the synthetic training data with 2000 design samples using the uniform Latin hypercube sampling method for each of the three housing archetypes including i) terraced, ii) detached and iii) Portiek apartments. The best-performing model in this instance included artificial neural networks with an R-squared above 0.95. The surrogate model is then integrated into the optimization workflow that forms the framework for an interface decision-making tool that users can use to generate optimal low-temperature ready refurbishment packages. The common low-temperature ready refurbishment packages include maximum airtightness, type C2 CO2 control ventilation system, cavity wall insulation, triple glazing, and internal roof insulation. Furthermore, it can be concluded that its more financially feasible to maintain existing radiators when transitioning to low-temperature heating instead of replacing the radiators with higher capacity. This is because the initial investment in other refurbishment measures not only improves comfort but also delivers significant energy savings that help reduce global costs in the long term.

There is an urgent need to address the shortage of student housing in Delft. However, the current design approach for student housing often fails to prioritize the creation of high-quality private spaces as well as social connections between individual housing units. While addressing the pressing need for more student housing, it is essential to reimagine the design of newly built accommodations to cater to both the private and social needs of students without compromising affordability.
The focus of the thematic research paper is to enhance the visual quality of students' private spaces through the use of computational evaluation. Recognizing the significance of factors like daylighting, outdoor views, and privacy in residential architecture, the study emphasizes the need to explicitly consider these factors during the early stages of the design process. By developing a parametric evaluation model, this research aims to evaluate visual quality in student dwellings and inform design decisions. The model is constructed based on conclusions drawn from literature review, interviews, and experimentation to identify visual quality parameters and provide clear visual data through heatmaps and number tags. This data helps highlight areas for improvement and allows for comparisons between different design alternatives.
The resulting project, Campus Village Delft, addresses the increased quality of private spaces by maximizing the hours of direct sunlight, view distance, and visual exposure representing the level of privacy. At the same time, the project aspires to create a community between the students, through carefully designed collective spaces, where unintentional encounters with your neighbors create a greater sense of belongingness.

The interior layout of apartments is made in the early design stage of an architectural project when the decisions can significantly impact the building's performance. During the early design phase, the ability to impact an architectural project is the most important, and this phase serves as the foundation of subsequent design phases. Proper daylighting improves visual comfort and minimises the dependency on artificial lighting. Combining good natural (day)lighting with a greenery view substantially affects the health and well-being of the building occupants. Optimising the layout of apartments based on daylight and view in the early stage of the building is crucial to ensure visual comfort. In this regard, artificial intelligence presents the potential to provide valuable support for performance-based decision-making in interior zoning based on daylight and view. However, there is currently a lack of machine learning methods to support designers in making informed decisions regarding early interior design decisions that affect daylight and view quality.
The performance of daylight and view quality significantly impacts the overall quality of residential spaces. The EN17037 guideline ensures the quality of indoor spaces by providing specific requirements for residential spaces regarding the view and daylight quality. The national annexe of the UK for daylight in dwellings should be included to ensure that daylight requirements align with the specific purposes of different rooms in dwellings. Incorporating adequate daylight exposure and good views in residential spaces promotes a connection to the natural environment, contributing to overall satisfaction and a higher quality of life for occupants, and leads to lower energy consumption and a smaller carbon footprint in buildings. Significant design parameters that impact the performance of daylight and view in residential spaces include the building orientation, window fenestration and the interior layout arrangement, specifically the room type orientation. Optimising the layout for optimal use of daylight and views is crucial for creating well-designed residential spaces that promote well-being, energy efficiency, and sustainability.
A novel ML design process workflow has been proposed to integrate ML models seamlessly into the architectural design process. Designers upload their layout designs into a dedicated tool, where the layout designs are pre-processed for compatibility with the ML model. Subsequently, the ML model predicts daylight and view values, which are then translated into practical visual representations during an after-processing step. A multimodal machine learning model utilising a ResNet and fully connected network is the most effective for predicting daylight and view quality in residential spaces. An ML model is trained using one image feature and five numerical features to predict the median daylight illuminance on the 21st of March, July and December and the p80 for ground and sky view inside a room. The trained model achieved a test loss MSE of 0.0047 and a test MAE of 0.0440 for the prediction of the three daylight labels, a test loss MSE of 0.0057 and a test MAE of 0.0478 for the prediction of the two view labels. An optimisation step identifies the optimal apartment layout based on a layout evaluation method guided by EN17037 requirements. A multifaceted approach is suggested for evaluating and improving residential layouts for visual comfort, incorporating a novel assessment system that evaluates daylight, view, and room orientation quality in each room to assess the overall apartment layout's visual comfort comprehensively. Overall, this framework represents a significant advancement in integrating ML models into architectural workflows by systematically evaluating daylight, view quality, and room orientation, providing visual feedback, and offering optimisation suggestions that align with contemporary design standards and requirements.

Acoustics combined with digital fabrication has been investigated for multiple years. Most research in this area has focused on the combination of acoustics and additive manufacturing. This is mainly due to the ability of this technique to create any geometry, which allows for very high absorption. However, it has the downside that additive manufacturing is quite expensive and the production process is time-consuming. Therefore, this study has chosen to put the geometry first and the performance of the resonators second.
To be able to produce a resonant panel based on Helmholtz resonators some additional knowledge was needed. Therefore, five experiments were performed to gain the knowledge needed to design the panel. The samples were printed using a fused filament printer and tested within an impedance tube located at the Faculty of Architecture in Delft. The experiments were concerned with:
- The position of the neck compared to the cavity: According to the results of the experiments the position of the neck has a minimal to no effect on the performance of the resonator.
- The crosstalk effect: According to the results of the experiments the effect of the crosstalk effect is minimal within the scope of this project. A small change in absorption was noticeable but so small as to be irrelevant.
- The effect of the cavity separation between two resonators: According to the results of the experiments the cavity separation can be removed without a large effect on the absorption of the resonators.
- The effect of the neck length on the width of the absorption curve: According to the results of the experiments a longer neck causes the width of the absorption curve to decrease.
- The impedance of resonators with L-shaped cavities: According to the results of the experiments an L-shaped cavity can be approximated by replacing the L-shaped cavity by a cavity with an identical horizontal section right below the orifice but altering the height, so the cavity has the same volume as the original L-shaped cavity.
After the experiments were done, a computational workflow was designed that is able to produce resonant panels based on the targeted frequency range and the possible size of the panel. The tool was theoretically verified using a case study. For the case study two panels were designed to improve the reverberation time for a room in the Faculty of Architecture. Using the Arau-Puchades method of calculating the reverberation time the panels showed to be effective at absorbing sound at low frequencies.

The building stock and the construction industry combined are responsible for a large share of greenhouse gases emissions. At the same time, every year tons of wood, paper and agricultural residues are wasted instead of recycled and upcycled into the production chain. In the fabrication field, the relevance of additive manufacturing processes is constantly growing, allowing for maximum customisation and optimisation of material and energy usage.
Lignocellulosic polymers are the most abundant in nature, although meanwhile cellulose is seen as a valuable raw material, lignin is treated as a by-product to be burned and generate energy. Based on the increasing use of both as fibre reinforcements and fillers in feedstocks for additive manufacturing, there is a potential to be explored.
The combination of the development of a novel material for an innovative fabrication process such as liquid deposition modelling, is the scope of work presented in this research.
Cellulose and lignin were studied, analysed and manipulated before mixing them with a vast selection of binding agents and additives. The outcome was evaluated according to a pre-established criteria set and documented, and a comparison drawn to define the best and most promising material mixes for additional investigation. From a universe of twelve mixes and numerous iterations for each recipe, four alternatives were picked for further characterisation and determination of their mechanical properties.
In parallel, the printability of the material considered as the most promising mix was explored through the extrusion of a sequence of simple geometries and shapes designed to understand and define the most adequate printing parameters. Limitations and challenges were observed and general directions and guidelines were documented.
With a complete dataset and overview of this novel bio-based and wood-based material for additive manufacturing, a simple structural node was designed. The fabrication of a prototype was used to further enhance the material properties and to clarify its potential and limitations for applications in the construction industry.
From the initial material exploration to the final prototyping phase, an extensive documentation was prepared to validate the potential and limitations of this novel material and indicate the directions for further research works.

In building design, the structural design is usually incorporated in the latter stages of the design, and the computational tools currently available focus more on converging and optimizing a single solution rather than providing an opportunity for the designer to explore design ideas. Incorporating structural design in the initial design phases can lead to more efficient and cost-effective structures, but in order to do so practical tools should be available to the designer to deepen the design space and allow them to efficiently explore it. Generative AI models could provide a solution to the problem and expand the design space by learning from the data provided.
This thesis explores such a solution by means of training an AI model (Variational Autoencoder) on an artificial dataset of 2D lattice patterns. To do that, a dataset of 6 unique 2D lattice patterns is created and used to train a simple VAE model. The methodology used in this thesis is to validate if an AI can aid in the exploration of design ideas by providing a larger design space with newly generated data that contain learned features from the dataset rather than through constraints set by the designers.
The results show that the VAE model can learn features and provide a greater diversity of design than the original dataset through newly generated designs. The output of the VAE model in this thesis is then explored for possible integrations into the design process for the early stages of design. For this, the generated patterns that are distinct and unique are identified and applied to a shell structure to explore topology design ideas.

This study intended to combine façade energy renovation strategies with circular design to improve energy performance and overall sustainability and circularity of the existing building stock. BIM technology can facilitate energy renovation projects by following circular design principles. A BIM library can offer most of the benefits of standardization, which is a crucial aspect of a successful circular design. The study's main research question was: “How can a BIM components library facilitate the design of a circular standardized façade renovation system that meets the energy-saving measures and it is adjustable?”It was intended to design a circular components library with BIM software that could provide the designer with the necessary information to help the design process of energy façade renovations. The library consists of standardized components and their different configurations so that the final façade system can be adjustable to different buildings. The library can provide the designers with all the information regarding the components' energy performance and circularity level by creating several evaluation indicators. The main focus of the design was the management of the data and the structure of the BIM library. The findings of the thesis are based on the research of the existing frameworks and guidelines and the “research by design” of the BIM library. The main stages of the thesis were the analog design of the circular standardized façade system and how it can be flexible, the digital design of the façade system with the creation of the BIM library, the validation of the design and the function of the library through the application to the case study building. The BIM library can facilitate the design process by:• Providing easy and quick accessibility to the different circular components of the façade system. • Grouping and organizing the components’ families of the library according to their function and relevance with other components of the system. • Providing information regarding energy performance and circularity with the evaluation indicators. • Counting the different components of the system and their different configurations. This can effectively contribute to the standardization of the system, the minimization of material waste and time, and it will improve its overall circularity level. This thesis provides a pragmatic perspective of the BIM library design and application and an instructional process for the user. It can be used as a starting point for these types of renovation projects. Further research and applications of the BIM library should follow this thesis approach. Also, changes need to be made to the data structure of BIM to improve the efficiency of the proposed library.

As the global population rise, climate conditions get more and more unpredictable, natural resources deplete; cities need to take action in order to sustain healthy living conditions as well as to ensure food safety. Currently, cities are solely dependent on external sources and suburban areas for natural resources and food as well as waste management. This linear metabolism results in cities consuming 60-80% of natural resources and producing 50% of waste globally. (Tsui et al., 2021) This problem can be overcome by introducing urban farming into cities by utilising waste and underused space as a resource for urban food production. Waste can be circulated in the city in order to generate a network of waste producing functions and farms.

There are urban farming systems which can digest waste and produce supplements for urban food production. However, the quest of choosing an urban farming system based on existing vacant spaces and waste flows is a complicated task. The complexity is a result of variables in the equation which may effect decision making such as different systems, waste types, vacant space characteristics as well as the size of spaces and the quantity of available waste. Moreover, in sites consisting of numerous vacant spaces and waste sources decision making is even more complex and laborious. If human designers were to perform this task then they would need to iterate countless times for each vacant space, each waste source close to it and each potential urban farming systems. However, when it comes iterating and repeating the same steps, computers are explicitly faster, time-efficient and error free. Therefore a decision making tool which can assist designers to choose urban farming systems based on existing conditions can be a practical resource.

This paper investigates how to integrate urban farming into cities by utilising under-used spaces and existing waste sources via using a decision making tool. The design rules and the methodology are formed based on literature review regarding different farming systems, varying waste flows and computational approaches. A prototype of the tool is generated and tested on 2 case studies in order to showcase the potential of such an approach combining food production with waste management.

Environmental noise has become a large health concern in Europe with at least one in five people exposed to levels considered harmful to health. Additionally, prolonged exposure to excessive levels of noise has a negative economic impact.
The rapid development of urban areas makes the effect of noise pollution even worse. However, architects and urban designers who define the shape of a neighbourhood rarely give attention to this aspect. Decisions regarding the sound environment are often taken in the latter stages of design when the least design exploration is possible. Moreover, environmental acoustic involves complex urban physics which makes it more difficult for designers.

Therefore, in this master thesis, a parametric simulation workflow is developed which can predict the traffic noise in the early phases of design. The approach would be easy to use for architects and urban designers to overcome some of the main drawbacks of traditional practices.

The project followed five-step processes of research, development, validation, testing and optimization. To better understand urban noise, atmospheric acoustics, and how buildings affect sound propagation, a literature review was conducted. The parametric workflow was then created using Grasshopper, the visual scripting plugin for Rhino3D, in conjunction with other plugins such as Pachyderm and Ladybug.

After development stage, the parametric workflow is validated against on-site measurements and Geomilieu (environmental noise calculation software). Further, the simulation results from the design stage demonstrate that the tool can include urban microscale features like building shape, façade extrusions and materiality which can have an impact on reducing the traffic noise levels. It is found that the building shape of the lower levels may amplify or quieten the sound on upper levels. Façade extrusions have the least impact but variations in their positions and sizes may influence the results. It was further predicted that the green façade has a great potential to reduce reflected noise and lower the values inside the courtyard.

In addition, the findings of the optimization study show that the workflow may be used with other performance criteria and help to explore design solutions. Overall, the workflow can help identify the relationships between design aspects and acoustic performance in the early stages of design by taking into account simplifications and restrictions such as edge diffraction.

In an urban context that needs to be constantly adapted to global crises, population movements, climate change and economic crises, designers and engineers strive to configure solutions that respond to multiple criteria. Within this framework, the concept of generative design is gaining more and more ground in the construction field, allowing rapid design space exploration, optimization and decision making for complex design problems.
This thesis implements an experiment in a common design problem such as optimizing the topology of shell structures for structural performance, using an Artificial Intelligence Framework. To implement this experiment a novel dataset consisting of various mesh tessellations is created. The next step is to design a generative workflow that combines unsupervised and supervised learning along with a Gradient Descent Algorithm for pattern generation, structural performance estimation and optimization. A Variational Autoencoder is trained to generate new mesh tessellations and a Surrogate Model is used to predict the structural performance of the decoded designs. Finally, a Gradient Descent Algorithm searches the latent space of the Variational Autoencoder for optimum solutions.
The results show that the proposed Artificial Intelligence workflow is able to generate novel and structurally better performing solutions that those existing in the training dataset. The findings of this thesis indicate that Artificial Intelligence can be successfully integrated into the concept of Generative Design to optimize shell structures.