Author: Amin Jalilzadeh

Promoters: Prof. Dr. Peter van Oosterom, Dr. Thaleia Konstantinou, Dr. Azarakhsh Rafiee

This research develops an integrated Digital Twin framework that transforms district-level energy planning from reactive infrastructure expansion to proactive, coordinated optimization. Traditional approaches treat buildings and energy grids as separate systems, leading to inefficient planning where building retrofits proceed without considering grid impacts, and grid expansions occur without leveraging building flexibility. This project addresses three critical gaps: the semantic disconnect between building and grid data systems, the temporal gap between operational insights and strategic planning, and the sequential dependencies in intervention strategies. The framework combines automated Urban Building Energy Modeling (UBEM) for the Netherlands, Physics-Informed Machine Learning for building optimization, Graph Neural Networks (GNN) for grid analysis and energy community formation, and Deep Reinforcement Learning (DRL) for strategic multi-objective planning. By creating a unified data infrastructure through Knowledge Graphs and enabling AI-driven optimization across scales and timeframes, this work advances Digital Twins from monitoring technologies to autonomous planning platforms. The framework enables data-driven pathways toward Positive Energy Districts by coordinating building-grid co-evolution, transforming how stakeholders navigate the complexity of district energy transitions while balancing competing objectives of decarbonization, affordability, and grid reliability.

Author: Yingwen Yu

Promoters: Prof. dr. ir Peter van Oosterom & Prof. dr. ing Uta Pottgiesser, Ir. Edward Verbree

This research project aims to design an Architectural Heritage Information Infrastructure (AHII) that integrates different digital models for structured and semantically enriched management of architectural heritage. The AHII will (1) collect digital data and information about architectural heritage, including point clouds, 3D Gaussian Splatting models, HBIM models, interactive maps, geo-referenced narratives, and audio-visual materials; (2) structure and semantically annotate this information according to international standards, partly to be further developed within the project; (3) manage the resulting assets in a heritage register/database; and (4) disseminate and visualize architectural heritage through web services that support viewing, downloading, and processing. Multiple use cases will demonstrate how the AHII supports systematic digital archiving, long-term preservation, and sustainable management of architectural heritage, while enabling flexible and timely integration of heterogeneous information layers among communities, researchers, industry, and other stakeholders. Ultimately, the AHII will provide both experts and the public with rich, multi-layered information and immersive virtual experiences of historic buildings and sites.

Author: Lisa-Marie Mueller

Promoters: Gabriele Mirra, Michela Turrins

The construction industry uses 50% of global raw materials, generates 30% of global solid waste, and contributes to 20% of carbon emissions. The reuse of materials is a key strategy for reducing the environmental impact of construction. Reinforcement learning (RL) models are uniquely suited to support decision making under uncertainty and to consider complex problems with a wide range of considerations. For reuse, RL models can support designers and engineers with a bottom-up, curiosity-driven approach to designing with reused materials. As using artificial intelligence (AI) becomes more common, the collaboration between engineers and these tools needs to be designed and considered to best integrate into the design process.

Author: Xuanchen Zhou

Promoters: Prof. Peter van Oosterom, Dr. Azarakhsh Rafiee

Wind and noise are both key environmental factors that can significantly impact urban livability, making them critical considerations in urban planning. Given the complexity of planning processes, where design decisions must be evaluated and refined iteratively, there is a strong need for accurate and timely feedback on the environmental impact of proposed urban layouts. A (near) real-time simulation system for wind and noise would greatly facilitate this process by enabling more informed and responsive decision-making. This PhD project focuses on developing a game engine-geographic information system (GIS)-simulation system to support this decision-making process. Through the seamless cooperation of those components, a fast and interactive system can be built. Using information from various web services, an urban digital twin that supports manipulation of scene elements can be constructed inside the game engine. The digital twin is then utilized to perform mesh-based wind simulation and ray tracing-based noise simulation. Through algorithm optimization and GPU acceleration, this project aims to achieve accurate and (near) real-time simulation results. Decision makers can interact with the simulation through multiple interfaces, receiving immediate and informative feedback of the wind and noise levels of current urban building layout.

Author: Berk Ekici

Promoters: Prof. dr. Sevil Sariyildiz, Prof. dr. Mehmet Fatih Tasgetiren, Dr. Michela Turrin

Keywords: High-rise buildings, Self-sufficiency, Energy, Food, Daylight, Performance-based design, Machine learning, Optimisation

Population growth and urbanisation trends bring many consequences related to the increase in global energy consumption and CO2 emissions and decrease in arable land per person. Alternative design proposals for sustainable living are on the agenda of researchers and professionals to respond to the needs of the 21st century for a sustainable future. Since the early examples in the 19th century, the high-rises have been one of the inevitable buildings of metropolises to provide extra floor space in compact cities. Based on the facts of the 21st century, high-rise buildings should fulfil more than provide extra floor space in the limited urban plot. This research suggests “self-sufficient high-rise buildings” that can generate and efficiently consume vital resources in addition to dense habitation for sustainable living. Optimisation of high-rise buildings has been the focus of researchers because of significant performance enhancement, mainly in energy consumption and generation. However, optimisation of self-sufficient high-rise buildings requires the integration of multiple performance aspects related to the vital resources of human beings (e.g., energy, food, and water) and consideration of large numbers of design parameters related to these multiple performance aspects. Hence, the complexity of self-sufficient high-rise buildings is more challenging than optimising regular high-rises that have not been addressed in the literature. The purpose of this dissertation is to present a framework for performance optimisation of self-sufficient high-rise buildings using artificial intelligence focusing on the conceptual phase of the design process.

Author: Ding Yang

Promoters: Prof. dr. Sevil Sariyildiz, Prof. dr. Yimin Sun, Dr. Michela Turrin

Keywords: Performance-Based Building Design, Optimal-Design Paradigm, Design as Exploration, Optimization Problem Re-Formulation, Multi-Objective Optimization, Multi-Disciplinary Optimization, Indoor Sports HallsTOC

There are an increasing number of optimal-design paradigms used in architectural design nowadays. In these paradigms, a design task is formulated, or partially formulated, as an optimization problem. Multi-Disciplinary Optimization and Multi-Objective Optimization, as two important optimal-design paradigms, have shown their great potential in improving the performances of complex buildings in recent decades. Nevertheless, current paradigms for ill?defined conceptual architectural design still lack ways to ensure the achievement of a reliable optimization problem, which hinders reliable design solutions despite the use of advanced optimization algorithms. To address this problem, it is necessary to shift the focus from Optimization Problem Solving to Optimization Problem Formulation. This research particularly focuses on knowledge?supported, dynamic and interactive Optimization Problem Re-Formulation in order to construct a new Multi?Objective and Multi-Disciplinary Optimization (MOMDO) method suitable for use in ill?defined conceptual architectural design. The proposed method consists of two subtype methods: Non?dynamic, Interactive Re-formulation method (Subtype-I) and Dynamic, Interactive Re?formulation method (Subtype-II), which can be used to explore design space in a convergent and divergent manner respectively. To support the re-formulation, various kinds of information and knowledge need to be extracted by utilizing different computational techniques, such as advanced sampling algorithms, Self-Organizing Map, Hierarchical Clustering, Smoothing Spline Analysis of Variance, Two-Level Variable Structure and modular programming. Moreover, a software workflow that can provide these computational techniques is developed; it integrates McNeel’s Grasshopper, ESTECO's modeFRONTIER and simulation software tools Daysim, EnergyPlus and Karamba3D. With the support of this software workflow, the proposed method is demonstrated via two case studies concerning the conceptual design of indoor sports halls.

Author: Ioannis Chatzikonstantinou

Promoters: Prof. dr. Sevil , Dr. Michela Turrinriyildiz

Keywords: Neural Networks, Decision Support, Complexity, Computational Intelligence, Architectural Design, Evolutionary Computation

Architectural design is a prime example of a complex task. The associated complexity often poses significant challenges to human cognition. As such, a systematic approach to design space exploration must be undertaken to maximize the potential for discovering optimal solutions to design problems. Recognizing the impact design complexity has on architectural design, this thesis proposes a comprehensive computational intelligence decision support system that combines components based on intelligence with ones based on cognition, with the ultimate aim of enabling decision-makers manage design complexity and improve decision making. This thesis adopts the theoretical standpoint that efficient navigation of an unknown environment assumes a fusion of intelligence and cognition. In this sense, and given the already widespread adoption of intelligent approaches (such as Evolutionary Computation), the main contribution of this thesis is to endow the intelligent approach with cognitive facilities, so as to improve its effciency to the point that it is readily applicable to the early stages of the architectural design process. Fusion of intelligent with cognitive approaches, as outlined herein, oIers the unique advantage of a decision support approach that is both powerful, owing to the extensive search capabilities of intelligent search algorithms, and flexible, owing to the extensive knowledge modeling capabilities of cognitive approaches. As such, it is uniquely suited to the early conceptual design stage where the need to explore large design spaces, flexibly redefine the design problem, and satisfy preferences that are not included in the primary design goals, are all paramount.The main output of this thesis is a comprehensive decision support framework; it is a framework, in the sense that it comprises a set of methods and implemented tools that seek to augment decision making in architectural design; it is termed comprehensive in that it employs computational cognition and machine learning to augment the intelligent decision support capabilities throughout the design decision support process. It is also generic and applicable as-is to a wide spectrum of architectural design problems. In the context of this thesis, validation of the proposed approach is performed mainly in case studies relevant to facade design, recognizing this design topic as a complexity-exhibiting exemplar in architectural design practice.

Author: Pan Wang

Promoters: Prof.dr.ir. I.S. Sariyildiz, Prof.dr.ir. Y. Sun, Dr. M. Turrin

Keywords: Indoor arena, computational design, multi-functional space, long-span roof structure

Indoor arenas are important public buildings catering for various activities (e.g., sports events, stage performances, assemblies, exhibitions, and daily sports for the public) and serving as landmarks in urban contexts. The multi-functional space and long-span roof structure of an indoor arena are highly interrelated, which impact the multi-functionality and structural performance and mainly define the overall form of the building. Therefore, it is crucial to integrate the multi-functional space and long-span roof structure to formulate proper forms for indoor arenas, in order to satisfy various design requirements during the conceptual design. This thesis aims at formulating a computational design method, ‘Computational Design of Indoor Arena (CDIA)’, to support the conceptual design of indoor arenas by using the computational techniques of parametric modelling, Building Performance Simulations (BPSs), Multi-Objective Optimizations (MOOs), surrogate models based on Multi-Layer Perceptron Neural Network (MLPNN), and clustering based on Self-Organizing Map (SOM clustering). In the formulation of CDIA, these techniques are modified, improved and organized into five components and three workflows, to satisfy the demands of the conceptual design of indoor arenas.

Author: Agung Indrajit

Promoters: Prof.dr.ir. P.J.M. van Oosterom, Dr.ir. B. van Loenen

Keywords: open spatial information infrastructure, urban plan, participatory monitoring, information interoperability, multidimensional representation

An urban plan contains a set of agreements from all stakeholders that may directly impact livelihood. However, many cities show a ‘plan and forget’ behavior by not monitoring and evaluating their urban plans. While local citizens are often excluded after the urban plan is enacted. Gibbs (2016) warned of the risk of this behavior by saying, “local communities are given the impression that the risk is being managed, when in fact it is not.” Therefore, as the affected party, local citizens should be included in the development of the plan and the monitoring, evaluating, and reporting of urban plan implementation. However, in reality, a collaboration between authorities and local citizens in monitoring land development is rare. In some cases, cities do not share urban plans with society. This situation motivates this research by developing a framework to make urban plans interoperable and accessible to the broader community by determining four particular objectives: (i) to identify what type and specification of spatial data are required to support participatory monitoring of the implementation of the urban plan; (ii) to design information interoperability of land-use plans for participatory urban plan monitoring; (iii) to construct spatial data governance that allows two-way information flows between stakeholders in participatory urban plan monitoring; and (iv) to develop a prototype for PUPM that enables two-way information flows and multidimensional spatial representation to support participatory urban plan monitoring. This study was built upon the four functions of land management: land tenure, land valuation, land-use planning, and land development. Information interoperability is essential for allowing interaction between these functions, particularly in PUPM. This study supports the revision of the ISO 19152 on the Land Administration Domain Model (LADM) by developing Spatial Plan Information Package (SP Information Package) for accommodating information from land-use planning and land development planning. In recent years, cities have adopted the digital twin concept to represent physical urban objects by exploiting 3D spatial information for improving the spatial thinking of all stakeholders. A common interest of urban planners in using an updated 3D spatial information for Rights, Restrictions, and Responsibilities (RRRs) was depicted for further analysis. Therefore, this study proposes the digital triplets concept for representing the legal situation of the land in four-dimensional representation (3D geometry with temporal aspect managed as an attribute). This thesis presents the development of a prototype using 4D spatial representation for supporting PUPM. The prototype enables two-way information flows between urban planners and citizens to enable the co-production of urban information. This study also proposes user-centered and data governance aspects in a holistic approach to implementing the proposed standard and technology, particularly for sharing RRRs with all stakeholders through an Open Spatial Information Infrastructure. The result of this study is implemented with actual urban plan data in the two biggest Indonesian cities: Jakarta and Bandung City. A usability test was conducted to assess the implementation of participatory urban plan monitoring using RRRs. The result shows that our approach can accommodate RRRs from the spatial planning process, providing a complete overview of the legal situation of the land or urban space to all stakeholders to monitor the implementation of urban plans to support the Sustainable Development Goals: ‘plan and progress’.

Author: Miktha Farid Alkadri

Promoters: Prof. dr. ir. arch. I.S. Sariyildiz, Dr. M. Turrin

Keywords: site analysis, point cloud data, attribute information, material properties, solar radiationTOC

As part of the passive design strategy, the development of computational solar envelopes plays a major role to construct a cooperative environmental performance exchange between new buildings and their local contexts. However, the state-of-the-art computational solar envelopes pose a great challenge in understanding site characteristics from a given context. Existing methods predominantly construct 3D context models based on basic architectural geometric shapes, which are often isolated from the surrounding properties of local contexts (i.e., vegetation, materials). Thus, they only focus on context-oriented buildings and energy quantities that unfortunately lack a contextual solar performance analysis. It is clear that this condition may result in a fragmented understanding of the local context during the design and simulation process. With the potential application of attribute point cloud information, it is necessary to consider relevant parameters such as surface and material properties of existing contexts during the simulation of solar geometries, which are currently absent in computational frameworks. As such, the new method is required to enable architects not only to measure specific performances of the local context but also to identify vulnerable areas that may affect the proposed design. This research focuses on exploring an integrated computational design method for solar geometry based on solar and shading envelopes, and geometric and radiometric information from point cloud data. In particular, two computational models consisting of SOLEN (Subtractive Solar Envelopes) and SHADEN (Subtractive Shading Envelopes) are developed, which are applied to temperate and tropical climates, respectively. In design practice, these models help architects to produce informed-design decisions towards high-performed building massing.

Author: Tiantian Du

Promoters: Prof.dr.ir. A.A.J.F. van den Dobbelsteen, Dr.ir. S.C. Jansen, Dr. M. Turrin

Keywords: Space Layout Optimization, Building Energy Performance, Parametric Design, Computational Optimization, Energy Simulation, Automatic Layout Generation, Lighting Energy Demand, Office Building Design

Studies have shown that space layout design can impact the building energy performance (BEP). However, its isolated effect on the BEP has not been identified yet. Performative computational architecture has proven to be effective to improve the BEP. However, only a few studies have tried to apply the performative computational architecture to space layout design. This research aims to investigate how space layout affects BEP, and to develop a computational optimisation method for space layout to improve the BEP of office buildings. Firstly, the mechanism on how space layout affects the BEP and how much energy is affected by space layout were identified through literature review and simulation. 11 layouts with different function allocations were simulated and compared. The outcome showed that layout variance affected lighting the most, and the maximum difference happened in Harbin, being 46% without shading and 35% with shading. As a follow-up, another literature review was conducted, which identified the functional requirements of space layout design, methods for automatic generation of space layout, and requirements for energy performance optimisation. In addition, a computational method was developed to optimise space layout design for energy performance improvement, regardless of functional requirements. As a result, the relationship between space layout and energy demands were recognised. In conclusion, space layout has proven to be a significant influence on the BEP, and conscientious design can improve it. For optimal energy performance, manual design of space layout is not feasible; in order to do that, a computational approach is needed.

Author: Haicheng Liu

Promoters: Prof. dr. ir. P.J.M. van Oosterom, Dr. ir. B.M.Meijers

Keywords: nD point clouds, space filling curves, continuous level of importance, histograms, skewed distributions, point set coverage, convex polytope query, flood risk mapping, AHN, benchmarks

In the Geomatics domain, a point cloud refers to a data set that records the coordinates and other attributes of a huge number of points. Conceptually, each of the attributes can be regarded as a dimension to represent a specific type of information, such as time and Level of Importance (LoI). Drastically increasing collection of high dimensional point clouds raises essential demand for smart and highly efficient data management solutions. However, effective tools are missing. File-based solutions require substantial development of data structures and algorithms. Also, with such solutions, enormous effort has to be made to integrate different data types, formats and libraries. By contrast, state-of-the-art DataBase Management Systems (DBMSs) avoid these issues, because they are initially devised for generic use of data. However, DBMSs still present limitations on efficiently indexing non-uniformly distributed points, supporting continuous LoI, and operating high dimensional data. These problems motivate the PhD research which focuses on developing a new DBMS solution. It is aimed at efficiently managing and querying massive nD point clouds to support different types of applications.

Author: Dejian Peng

Promoters: Prof.dr. C. Wagenaar, Prof.ir. P.G. LuscuereProf.dr. C. Zhang

Keywords: patient journey, process, patients’ satisfaction, performance

Nowadays, we are faced with serious challenges in public health worldwide. However, the challenges cannot be solved only in the domain of architecture, medical science or management. A successful hospital building is more than a nice building or an efficient healing machine. Patient journey is such a concept that tries to explore the possibility to solve the problems in hospitals in the domain of hospital architecture and hospital management. In this context, the research proposes a study of patient journey in hospitals from the perspective of architecture on basis of the outcomes achieved in management. Patient journeys are transferred from both clinical and administrative processes to special patterns. Moreover, in such a visual way, both the efficiency and effectiveness of hospitals and patients’ satisfaction during the journeys in hospitals are analyzed with case studies of China and the Netherlands. The system of spatialized patient journeys helps architects and hospital managers broaden their understanding of hospital. And the comparison results from case studies are useful for hospitals in China to improve performance and patients’ satisfaction.

Author: Lia Marie Tramontini

Promoters: Prof. Dr.-Ing. U. Knaack, Dr. M. Turrin, Prof. Dr.-Ing T. Klein

Keywords: Freeform architecture, Façades, Additive manufacturing, Masscustomized fabrication

The thesis, titled ‘Towards the Integration of Additive Manufacturing for Freeform Steel and Glass Façade Construction,’ explores the transformative role of additive manufacturing (AM) in enhancing the design and construction of Freeform Steel and Glass Façades (FFSGF). These façades involve intricate components, necessitating collaborative efforts among designers, engineers, and fabricators to achieve complex façade geometries with good performance while ensuring efficiency in design, material usage, fabrication, and cost. Recent advancements in AM technology have made it a potentially viable and increasingly accessible fabrication strategy, particularly for mass-customized components such as those used in freeform construction. The research aims to answer the central question of how AM can effectively contribute to developing node solutions supporting Freeform Steel & Glass Façade (FFSGF) construction.The study systematically examines opportunities for improvement in existing solutions. Chapters 2 and 3 provide a critical overview of FFSGF construction typologies and explore the current landscape of AM in façade applications. Chapters 4 and 5 delve into the design and development of crucial components—structural nodes and gasket nodes—utilizing different AM technologies. Prototypes are manufactured and evaluated in comparison to existing solutions. Chapter 6 provides a case study of integrating AM product development into a larger construction project, emphasizing interdisciplinary collaboration. The thesis underlines the advantages of the systemization of AM node design throughout the design and fabrication of AM nodes. This research contributes to the evolving knowledge at the intersection of design, engineering, construction, and AM, aiming to provide a valuable resource for building industry professionals navigating the complexities of incorporating AM into the fabrication of freeform steel and glass façades.

Author: Abdullah Alattas

Promoters: Prof.dr.ir. P.J.M. van Oosterom, Prof.dr.techn. S. Zlatanova

Keywords: LADM, IndoorGML, indoor navigation, access rights, database

Indoor navigation applications are actively investigated and developed due to their capacity to provide users with essential information in the modern extensive building complexes. Therefore, many researchers have developed a range of indoor navigation applications, which have focused on aspects such as localization, indoor route computation, and human spatial cognition. Unfortunately, current indoor navigation systems do not consider the user's access rights when it comes to navigating safely and effectively. This thesis delivers several contributions, which are based on international standards, to provide Indoor navigation aware of the user’s access rights. The thesis proposes: 1) a combined model of ISO’s LADM and OGC’s IndoorGML; 2) an enhancement of the UML class diagram of the conceptual model of IndoorGML; 3) a 2D LADM country profile of the Saudi Arabia; 4) a 3D LADM country profile of Saudi Arabia; 5) a conversion of the combined LADM and IndoorGML conceptual model to a technical model; 6) definitions of access rights for users of indoor environments during crisis based on the integrated model of LADM and IndoorGML; 7) a 3D web-based prototype application for indoor navigation making use of user access rights. The developed concepts and implementation have been acknowledged by the standardization organization ISO and OGC and considered for amending IndoorGML and LADM.