Faculty-funded PhD studentships

The Faculty is offering up to four PhD studentships for January 2024 entry. Projects from which studentship applicants must select are listed in the links below; no other projects will be considered. (see Project Proposals).

Applicants are strongly encouraged to contact the project's first supervisor to discuss their interest before making an application.

Closing date for applications: 13:00 on 30 November 2023

How to apply

You must include the following in your application:

  • Online application form, available here (please ensure you select the correct faculty)
  • Statement of the title of the project(s) for which you are applying and the first supervisor's name (upload this as a separate Word document) – if this is not included, your application will not be considered for a studentship. A project proposal and timeline is not required with the application, but those shortlisted for interview will be required to send a full proposal and timeline a week before the interview.
  • An academic CV
  • Copies of your academic certificates and transcripts (degree level onwards) – applicants must have at least an Upper Second or First Class Honours degree
  • A copy of your English language qualification, if applicable (must be dated no earlier than March 2022) – see our English language requirements webpage for information about which qualifications are accepted
  • References will only be required for applicants invited to interview. References should be from professional or academic contacts and cannot be from family members or friends. At least one reference should be from someone who knows you from your most recent academic qualification (but is not a member of the supervisory team for the project).

If you are applying for more than one project, you must submit only one application form, but include the titles of all the projects for which you are applying. If more than one application form is received, only one of them will be considered.

Please ensure that all required documents are submitted together with your application form as we are unable to consider incomplete applications or documents sent separately.

If you have not heard from us by four weeks after the closing date, your application has been unsuccessful

Interviews will take place online, on 9, 10 and 11 January 2024

Funding available

  • Home tuition fee plus £20,622 stipend x 3 years

International applicants will be required to pay the difference between the Home and International tuition fee each year (£12,000 approx for 2023-24)

All research students in the Faculty are charged a bench fee each year, which is not covered by the studentship. The amount depends on the resources required for the project; the minimum is £500 full-time.

Project proposals for Faculty-funded PhD studentships

Please see the project proposals for PhD study, listed under the Faculty's Schools.

School of Computer Science and Mathematics

Simulation-based Quantum Machine Learning for Advancing AI

We are seeking a highly-motivated candidate to pursue a PhD opportunity in the exciting and rapidly growing field of simulation-based quantum machine learning to shape the future of AI and quantum computing. As a member of our research team, you will have the opportunity to explore the cutting-edge intersection of quantum computing and machine learning to develop novel algorithms that can handle complex data structures and solve problems intractable by classical computing.

Research focus:

Your research will involve working on the development and implementation of simulation-based quantum artificial intelligence and machine learning algorithms and models. The innovations will be applied to address real-world challenges across various domains such as healthcare, finance and energy. Your research journey will commence with the design and simulation of elementary machine learning circuits and progressively advance to more complex quantum deep learning network such as Quantum Convolutional Neural Networks (QCNN).

Leverage leading tools:

You will work with a range of python-based open-source quantum software platforms and toolboxes, including IBM Qiskit, Google Cirq, Quantum Virtual Machine, cross-platform Python library PennyLane, and QuTip.

Diverse research directions:

Within this project, there are several potential research directions to explore, including:

  • Developing and implementing quantum machine learning algorithms for financial applications, like fraud credit card transaction detection.
  • Enhancing medical diagnoses and treatment planning using QCNN to analysis large datasets of patient information and medical imaging for applications such as dementia diagnosis.
  • Applying quantum machine learning to optimise resource allocation, increase efficiency and reduce carbon emissions in energy systems.

Additional opportunity:

In addition to your research, you will have the opportunity to receive specialised course and tutorial training on Quantum Machine Learning, collaborate with researchers in the fields of quantum computing and machine learning and participate in conferences and workshops to present your research findings.

The ideal candidate:

The ideal candidate will have a strong background in computer science, physics, optical communications, mathematics, or a related field, with a keen interest in machine learning, artificial intelligence and quantum computing. While prior experience with quantum mechanics, quantum circuit design, linear algebra, programming languages like Python, Tensorflow, and simulation software such as Qiskit or QuTiP is desirable, it is not a requirement.

If you are passionate about advancing the frontiers of AI through simulation-based quantum machine learning, we encourage you to apply. This is a unique opportunity to pursue a PhD in a cutting-edge and rapidly-growing field with significant potential for impact and innovation. Join our team and help shape the future of AI and quantum computing.

Supervisor: Dr Xing Liang

View Dr Xing Liang's profile and contact details >

EcoGuardian: Transforming Urban Sustainability with AI-Driven Air Quality Solutions

This project aims to construct an autonomous computer system (purposeful AI) that continuously collects and analyses datasets from various sources, to support fast-paced data-driven decision-making when dealing with recent or emerging crises. We take motivation from the recent rise of global crises (i.e., COVID-19, adverse weather, mineral shortages etc.) that have posed challenges to national and international decision-making bodies.

Using a deep learning-based approach, this artificially intelligent machine will use existing open-access research outputs to perform causal modelling on incoming data streams. The machine will autonomously select topics within a crisis context (i.e. analyse traffic data to suggest emission control measures). A fully-functional model will compute potential options for an ongoing crisis using real-time data while forecast and recommending preventive measures using synthetic data.

In this research project, an initial machine will be built to analyse historical air quality data from major British cities and relevant research articles in the first phase of the project. Following the automatic analysis of full-text publications, we will analyse air quality index data from major cities of the United Kingdom and test how major events, or initiatives impacted the trends. For example, from transport-induced pollution, we will use our machine to analyse the long-term change in air quality index before and after the COVID-19 lockdown and introduction of clean air zones. An expected outcome of this exercise will be a data-supported recommendation to implement low-emission zones and clean air-zones in major cities.

The project team will include computer scientists from the School of Computer Science and Mathematics, Kingston University, project team's industrial collaborator (Techno Commconsulting Ltd UK), and experts from environment departments of Kingston University and local councils (Kingston and Ealing councils). The project activities will include research into AI/Deep learning method development, liaison within the research team and with external partners, and presentation of work at project meetings, technical sessions, and scientific meetings.

Applicants should have, at least, an honours degree with a 2.1 or above (or equivalent) in Computer Science, Physics or related disciplines. In addition, they should have an excellent programming skill in Python in an academic or industry setup, good mathematical background and an interest in machine learning and purposeful collaborative AI.

Supervisor: Dr Farzana Rahman

View Dr Farzana Rahman's profile and contact details >

Revolutionising Connectivity of Medical Wearable Devices: Harnessing Deep Learning to Enhance Network Performance and Sustainability

With the promise of unprecedented data speeds, near-zero latency, and ubiquitous connectivity, 6G networks are poised to revolutionise industries ranging from healthcare to autonomous vehicles. This represents a pivotal moment in wireless communication history, offering a canvas for innovation that few could have imagined. However, with great power comes great responsibility. The surging demand for wireless connectivity and the proliferation of energy-intensive devices pose profound technical and environmental challenges.

By focusing on the millimeterWave band and energy efficiency, this project aims to provide targeted and impactful contributions to improving the performance and sustainability of networks, especially in the context of IoT and emerging high-data-rate applications aimed at the development of advanced medical wearable devices. Indeed, such technology will enable a new generation of applications such as remote health monitoring, early disease detection from health data collected in real time, and wearable implants.

At the intersection of millimeterWave communication, energy efficiency, and healthcare, this research not only addresses critical challenges in wireless technology, but also has the potential to save lives, improve healthcare outcomes, and enhance the quality of life for individuals worldwide.

Research objectives

This PhD project will centre its research on the following specialised objectives, with a primary focus on the millimeterWave band and energy efficiency in wireless communication:

  • MillimeterWave Band Utilisation: Investigate and develop machine learning-driven techniques tailored to its unique characteristics. This includes exploring advanced beamforming, channel estimation, and interference management strategies to optimise millimeterWave spectrum utilisation.
  • Energy-Efficient MillimeterWave Communication: Design and implement energy-efficient protocols and algorithms for millimeterWave communication, with a particular emphasis on IoT devices. Explore novel machine learning approaches to reduce energy consumption while maintaining high data rates in millimeterWave networks.
  • Cross-Layer Optimisation: Explore cross-layer optimisation techniques that integrate machine learning at various protocol layers to enhance both spectral efficiency and energy efficiency in millimeterWave wireless networks.
  • Real-World Validation: Validate the proposed solutions through rigorous simulations and practical implementations in millimeterWave communication scenarios, ensuring their effectiveness and real-world applicability for medical wearable devices.


The project will involve theoretical research, simulations, and practical implementations. Machine learning algorithms, especially deep learning, will be leveraged to tackle the unique challenges of wireless communication. Real-world datasets and experiments will validate proposed solutions in the context of medical wearable devices.

Expected outcomes

This research initiative seeks to contribute to the advancement of wireless communication technology through the application of machine learning. The anticipated outcomes include improvements in spectrum efficiency, network security, and energy-efficient protocols for emerging IoT applications, especially in the area of medical wearable devices.

Supervisor: Dr Neda Ahmadi

View Dr Neda Ahmadi's profile and contact details >

Enhancing Privacy in Conversational AI: A Comprehensive Framework for User-Centric Development and Implementation

The ascent of conversational AI platforms, such as virtual assistants and chatbots, has revolutionised how humans interact with technology. While these systems promise efficient, human-like interactions, they raise significant concerns regarding user data privacy. As conversational AI begins to understand and simulate human emotions, behaviours, and preferences more precisely, ensuring that the data used does not violate user privacy becomes imperative. This PhD research will dive deep into the intricate world of conversational AI, aiming to bridge the chasm between advanced technology and the ethical considerations that underpin it.

The critical nature of this research stems from the strategic priority of safeguarding sensitive and personalised information shared by users. As the digital realm grows, ensuring the public's trust in AI technologies becomes increasingly vital. By aligning with the broader vision of pioneering responsible AI development, this project aims to place the UK at the forefront of combining innovative technological advancements with ethical considerations.

Research Aims:

  • Investigative Analysis: Understand the prevailing privacy dynamics within conversational AI systems. This entails identifying the inherent vulnerabilities and gaps in current platforms, allowing for an informed foundation upon which subsequent aims can be built.
  • Development of a Comprehensive Framework: Using advanced techniques, such as differential privacy and homomorphic encryption, the goal is to design a robust framework focused on user-data protection. This framework will address the technical challenges and ensure transparency in how AI systems operate and interact with user data.
  • Ethical Considerations in AI: Beyond the technicalities, a significant portion of this research will emphasise embedding ethical considerations into conversational AI development. Ensuring that AI systems respect user privacy and operate transparently is paramount, making it crucial to devise strategies that uphold these values while enabling the AI's advanced functionalities.

By the end of this three-year PhD journey, the candidate will have made significant strides in marrying technology with ethics, pioneering a blueprint for future conversational AI systems that resonate with data privacy principles and user-centricity.

Supervisor: Dr Hu Yuan

View Dr Hu Yuan's profile and contact details >

Enhancing Pulmonary Disease Diagnosis with Deep Learning: A Path to Precision Medicine.

Convolutional neural networks (CNNs) excel in medical image analysis, handling tasks like disease classification, tumor segmentation, and lesion detection by extracting local features. In recent developments, transformers have been employed for a wide range of clinical applications in medical imaging, including reconstruction, registration, segmentation, detection, and diagnosis. Multi-modal medical images such as CT, MRI, SPECT, PET with their explicit long-range dependencies, can enhance deep learning (DL) model performance compared to natural images.

Pulmonary diseases like tuberculosis (TB), bacterial pneumonia, and viral pneumonia carry the dual threats of contagion and fatality, posing significant risks to public health. Timely and accurate detection of these illnesses is vital, enabling healthcare professionals to administer prompt and effective treatment. Thus, the effective and precise diagnosis of these diseases holds paramount importance. Conventional diagnostic procedures necessitate extensive manual interpretation, introducing the risk of errors and delays in patient care. In recent years, DL techniques have surfaced as potent tools for automating the classification of pulmonary diseases.

The challenges associated such as limited and data imbalance, data quality, inadequate pre-processing, covariant shift, biases and fairness, labelling error, overfitting, data privacy and regulations, etc. with the medical image classification and segmentation can have a direct relationship on the final performance of any DL model. Due to its composite formation, dealing with CXR images becomes difficult when it is infected, for example, widespread ground-glass opacities and diffuse reticular-nodular opacities. This makes the computerised recognition of pulmonary disease employing CXR imaging a challenging job. Furthermore, the available DL-base model for pulmonary disease classification are lacking to address the local and global relationship of features and challenges of poor data quality resulting in lower accuracy.

By addressing the aforementioned challenges and harnessing the capabilities of artificial intelligence, this PhD. project strives not only to develop an efficient DL-based approach for pulmonary disease classification but also to explore contributions to the broader implementation of cascaded DL models. Through these innovative research endeavours i.e., DL- base cascaded approaches; our goal is to bridge the existing research gap in pulmonary disease classification, particularly in the context of multi-classification challenges.


The research methodology encompasses the following key components:

  1. Data Collection: Curate comprehensive CXR datasets representing a range of pulmonary diseases, including viral pneumonia, bacterial pneumonia, TB, and normal cases.
  2. Extensive Pre-processing: Address data quality issues, manage outliers, and employ dimensionality reduction techniques to optimise the dataset for modelling.
  3. Model Development: Create and implement an AI-driven cascaded DL model tailored specifically for pulmonary disease classification.
  4. Model Evaluation: Conduct a series of meticulous experiments and performance assessments, followed by iterative model refinement to attain optimal outcomes.
  5. Performance Metrics: Choose relevant performance metrics, including precision, recall, F1-score, and others, to ensure a comprehensive evaluation of the model's effectiveness.
  6. Ethical Considerations: Integrate a thorough assessment of ethical and privacy concerns into the research methodology to safeguard sensitive information and adhere to ethical standards.

Applicants should have an honours degree with a 2.1 or above (or equivalent) in Computer Science, Physics or related disciplines. In addition, they should have excellent programming skills in Python in an academic project, good mathematical background and an interest in ML, DL, and intended collaborative AI.

Supervisor: Dr Tariq Rahim

View Tariq Rahim's profile and contact details >

Automated Protein Structure Annotation with Advanced Language Models

This project does not require any previous knowledge of Biology.

Proteins are the building blocks of all living organisms' cells. Many types of cancer as well as Alzheimer's disease, Parkinson's disease, Mad-cow disease, and others are all associated with protein misfolding. Everyone has memorised the ‘logo' of COVID-19: that grey Styrofoam ball dotted with red spikes. Those red spikes have been considered the most ‘famous' part of the virus since they are crucial not only to their ‘attack job' in human bodies but also as a target of most vaccines. COVID-19's red spikes are simply proteins. Therefore, any new insight into the structural and functional features of proteins is considered invaluable to biologists, drug and vaccine designers.

In the past few years, AI, using deep learning techniques, has successfully and brilliantly solved a puzzle that had challenged scientists for more than five decades. DeepMind developed a computer program called AlphaFold that is capable of predicting the structure of any protein from its amino acid sequence alone. Since then, protein structures have been pouring into the Protein Data Bank (PDB) at an unprecedented rate. Ideally, all structures should be annotated and classified in two popular databases: CATH and SCOP. One of the main reasons for annotating protein structures is to gain insight into the molecular basis of their functions. Additionally, such annotations may help connect different proteins with possible evolutionary relationships, a crucial step toward fully understanding any protein. In both databases, annotations involve some human intervention, which has created a new challenge: the need for a fully automated way to classify the vast number of protein structures being deposited every day.

There have been several attempts to build a machine learning/deep learning model for this task. Earlier this year, the CATH team developed a sequence-based neural network model to predict a protein's superfamily, called CATHe, where 'e' stands for embeddings. This term is used to denote the numerical representations of protein sequences obtained from a hot topic called protein language models (pLMs), inspired by the well-known subject of Natural Language Processing (NLP). The best model was the artificial neural network (ANN), which reported an F1 Score of approximately 0.72% on a dataset containing the largest 1,773 superfamilies. Despite the relatively high F1 score on such a large number of classes (1,773), such a model cannot be considered reliable for annotating proteins.

This project aims to leverage state-of-the-art techniques used in NLP to develop two new pLMs: one for protein sequences and the other for the sequence of Structural Alphabets (SA). The goal is to build a model that accurately annotates more than 200 million protein structures deposited so far in the AlphaFold Database – AlphaFold DB.

Supervisor: Dr Jad Abbass

View Dr Jad Abbass's profile and contact details >

School of Engineering

Fast Robotic Disassembly for Improving WEEE Recycling

In the pursuit of addressing the ever-growing concern of electronic waste (Waste Electrical and Electronic Equipment or WEEE), this research project embarks on a transformative journey to develop fast and efficient robotic disassembly methods aimed at enhancing WEEE recycling. The goal of this three-year Ph.D. research endeavour is to significantly contribute to the reduction of electronic waste in landfills, the recovery of valuable resources, and the overall environmental sustainability of the electronics industry.

The management of electronic waste has gained critical importance, given the rapid evolution of technology and the increasing volume of discarded electronic devices. In 2019, a staggering 53.6 million tons of E-waste were generated globally, with a shocking 82.6% of it ending up in landfills or being illicitly discarded. The improper disposal of electronic waste not only wastes precious resources but also poses severe environmental and health risks.

Robotic disassembly offers a promising solution, enabling the efficient retrieval of valuable materials from discarded electronics. However, existing methods are often specific to particular objects and lack versatility and cost-effectiveness. To address these challenges, this project introduces a comprehensive approach to fast robotic disassembly, encompassing both the reengineering of objects and the development of a robust robotic platform.

The primary focus of this project is to create a versatile robotic disassembly platform capable of disassembling a wide variety of electronic products with minimal modifications. Unlike traditional approaches that rely on complex, object-specific robotic cells, this platform will be adaptable, cost-effective, and scalable. A crucial aspect of this project involves the redesign of electronic objects to facilitate robotic disassembly. By optimising the design of casings, they become easily accessible and manipulatable by the robots within the cell. This might include incorporating features like snap-fits while eliminating screws, streamlining the disassembly process.

Beyond conventional disassembly techniques, this project delves into the integration of machine learning and computer vision to enable the robotic platform to autonomously identify and recognise objects. Using cameras and advanced machine learning approaches, the system will be trained to distinguish various objects from a pre-defined list stored in a database, selecting the appropriate disassembly procedures based on the object's unique characteristics.

This PhD research project will adopt a multidisciplinary approach, drawing upon principles of robotics, automation, machine learning, computer vision, and sustainable design. The project will unfold in several phases:

  • Robotic Cell Development: The first phase will focus on creating a robotic cell, employing the Quanser QArm robot (already available in our lab) as the manipulator. This cell will be configured to disassemble a known object, chosen for its representative variety of electronic components. This practical experiment will allow us to assess the feasibility of automated disassembly using existing equipment.
  • Object Redesign: Simultaneously, the student will embark on the redesign process for the chosen object. The focus will be on optimizing its design for robotic disassembly. The incorporation of features such as snap-fits and the removal of screws will be explored to enhance efficiency and reduce complexity.
  • Camera-Based Object Identification: The subsequent phase will involve integrating machine learning and computer vision to enable the system to autonomously identify and recognize objects from a predefined list. This will set the stage for adapting disassembly procedures based on object-specific characteristics.

Expected outcomes:

By the end of this PhD research project, we anticipate the development of a versatile robotic disassembly platform that can adapt to a wide range of electronic products. This platform will significantly contribute to WEEE recycling, with enhanced resource recovery and reduced environmental impact. Moreover, the integration of machine learning and computer vision for object identification will further improve the platform's autonomy and adaptability. In conclusion, this PhD research project represents a ground-breaking endeavour to address the pressing issue of electronic waste through fast and efficient robotic disassembly, making the process both sustainable and cost-effective.

Supervisor: Dr Claudio Gaz

View Dr Claudio Gaz's profile and contact details >



Development of Novel Thermochemical Heat Storage for Waste Heat Recovery

The rising demand for sustainable and efficient energy management has brought attention to the vast amounts of waste heat produced by industries. Heavy industries emit a significant portion of their consumed energy as waste heat. Harnessing this energy, characterised by high energy density and minimal energy loss during extended heat storage, holds a transformative potential for industrial sustainability and environmental conservation.

The central focus of this PhD research lies in the comprehensive study and enhancement of Salt-In-Matrix (SIM) thermochemical heat storage materials. Thermochemical sorption using salt hydrates offers promising avenues due to its high energy density and near-zero energy loss during prolonged storage. However, the pure salt hydrates face thermodynamic and kinetic challenges during their hydration and dehydration phases. The project aims to address and optimise these challenges by:

  • Material Design and Synthesis: The design and formulation of optimal SIM compositions to enhance thermochemical properties. This involves understanding the interaction between various salts and matrices to achieve the best heat storage potential.
  • Material Performance Assessment: Evaluate the charge and discharge cycles of SIM materials for energy density, heat release rates, and overall efficiency. This will also involve studying the material's lifecycle, including its performance over multiple cycles and understanding material degradation over time.
  • Kinetics and Mechanism: Investigate the reaction kinetics of salt hydrates. By developing kinetic models, the intention is to forecast the heat storage performance of materials, aiding the design and fine-tuning of real-world systems. The intertwined process of heat and mass transfer, inherent in thermochemical sorption heat storage, will be a significant point of investigation.
  • Reactor Design and Optimisation: Design and optimisation of the reactor are important. By modifying reactor structures, we can improve gas diffusion paths and increase heat exchange areas, promoting faster reactions and higher output power. Furthermore, understanding reactor corrosion and strategizing to reduce such occurrences will be crucial.
  • System Integration and Performance: Examine how SIM materials can be incorporated into larger systems. This involves understanding the dynamics of closed systems (with periodic vacuum requirements due to non-condensable gases) versus open systems (which can directly exchange mass and energy with the environment but require airflow mechanisms).
  • Application in Coupled Systems: Evaluate the feasibility and efficiency of SIM materials in coupled systems. While these systems can boost seasonal stability and schedulability, challenges lie in initial costs and system adaptability.

The future of energy conservation and sustainability lies in innovative solutions. This PhD position, deeply embedded in advanced material science and thermochemical research, promises to pioneer new pathways for harnessing waste energy. Through the extensive study and enhancement of SIM materials, this position aims to contribute a vital piece to the puzzle of sustainable energy management.

The ideal candidate for this PhD position should have a strong background in renewable energy and material science with a keen interest in thermochemistry. Proficiency in simulation software such as COMSOL Multiphysics, ANSYS Fluent, or MATLAB for modelling thermochemical processes is crucial. Their commitment to addressing waste heat challenges, along with analytical skills and innovative thinking, is essential. Collaborative teamwork and prior experience in heat storage and simulation are advantageous.

Supervisor: Dr Sahand Hosouli

View Dr Sahand Hosouli's profile and contact details >

School of Built Environment and Geography

Integrated design approaches of thermo-active building envelope for near zero carbon buildings and environmental sustainability

The construction sector has seen a high share of energy-related carbon emissions globally due to building operation, posing a great threat to achieving net zero carbon targets by 2050. According to the Global Status Report for Buildings and Construction, in 2021, the buildings and construction sector accounted for about 34% energy consumptions and circa 37% of energy-related carbon emissions globally. The split share of operational carbon emissions from residential and non-residential buildings is around 28% (with the remaining 9% from construction industry). The operational carbon emissions of new buildings in compliance with current Building Regulations in the UK predominates the building whole life carbon (circa 2/3), using conventional passive solutions for the building envelope design. To tackle the challenges of developing near or net zero carbon buildings for environmental sustainability, it is promising to develop thermally active building envelope, which has a great potential to reduce building energy demands and operational carbon by 50% or more, respectively.

The research project aims to delve into integrated design approaches of novel thermo-active building envelope for near or net zero carbon buildings, using the iconic building Town House at Kingston University London as an archetypal building. Both passive and active solutions for energy-efficient building design will be explored and analysed based on building performance modelling and simulation (e.g. EnergyPlus, IES VE, TRNSYS). It is further expected to extract new key thermal indexes that can characterise the thermal behaviour of thermo-active building envelope in a simple way for engineering applications. Climate-responsive integrated design approaches of buildings in the UK will be ascertained, especially for commercial buildings with the archetypal building Town House.

The Town House, built in 2020 and located on the Penrhyn Road Campus at Kingston University London, is recognised as an energy-efficient building, with the features of good thermal insulation and built-in heat recovery systems, as well as rooftop solar photovoltaic, etc. Especially, a thermo-active system was embedded in the concrete slabs as part of the building envelope, allowing building mass to passively heat and cool the interior. The Town House has won the 2021 Royal Institute of British Architects (RIBA) Stirling Prize (an indicator for Britain's best new building), as well as 2022 EU Prize for Contemporary Architecture – Mies van der Rohe Award (recognised as the highest accolade in European architecture). It is interesting to assess the building performance of its thermo-active building envelope (or components) to inform the practical building energy efficiency and compare with the current Building Regulations for environmental sustainability assessment. In the meantime, some other novel active solutions such as thermally active insulation, pipe-embedded walls, PCM heat storage walls, facade integrated solar photovoltaic / thermal collectors, the thermoelectric battery, etc. can be integrated to improve the thermal performance of thermo-active building envelopes, further reducing the building energy demands and carbon emissions. The research will provide insights into developing near or net zero carbon buildings, in contrast to the new building design in terms of the current Building Regulation in the UK. It will have impact on addressing contemporary construction methods for architects, building engineers, and construction-related stakeholders to reference, as well as decarbonising new buildings for contribution to the net zero carbon targets in the long run.

Supervisor: Dr Jie Deng

View Dr Jie Deng's profile and contact details >

Innovative Façades in a Zero-Carbon Future: Harnessing AI for Predictive Building Performance

As the global community grapples with the pressing challenge of mitigating climate change, the building sector emerges as a key player in the pursuit of a zero-carbon future. Innovative façade designs, pivotal in sustainable building, offer a promising avenue to reduce carbon footprints. The next generation of façades is smart, adaptive and complex.

However, a significant challenge remains: accurately predicting their performance in the built environment. The intricate spatial and temporal dimensions of these innovative façades necessitate advanced modelling techniques that can anticipate outcomes across diverse scenarios. Current methodologies, heavily reliant on human intervention, often compromise both accuracy and efficiency, rendering them unsuitable for evaluating the increasingly complex building façade system designs. A transition to more automated methods is crucial to gather the robust datasets essential for enhancing our predictive modelling capabilities.

This studentship aims to explore the potential of AI in transitioning from traditional physical models to data-centric models. In doing so, it seeks to develop methodologies and tools that amplify the broader application of AI in building performance modelling and simulation, all while championing the integration of innovative façades in architectural design.

The student will embark on a comprehensive journey, beginning with the compilation of complex façade types and delving deeply into their key parameters and effects. This exploration will extend to advanced modelling and simulation of these façades, with a particular focus on daylight, energy and indoor conditions. A significant portion of the research will be dedicated to understanding the capabilities of AI in delivering relevant data, especially robust measures of façade performance. To ensure the accuracy of these models, the student will engage in real-time site monitoring to validate and calibrate simulation outcomes. This hands-on experience will be complemented by curating a robust database, merging calibrated data, monitoring records, and extracting building performance data from various sources. The culmination of this endeavour will be the transition from a conventional modelling approach to a data-driven assessment model. The student will then assess the precision of this model by comparing predicted façade performance against actual building data. Throughout this academic journey, the student will spend time at various research facilities, gaining insights from diverse façade applications and methodologies.

The student will have a unique opportunity to broaden their perspective in a highly multi-disciplinary domain. The student will collaborate with a supervisor who has a distinguished track record in building engineering, notably in areas such as zero-carbon design and sustainable building technologies. Complementing this expertise, another supervisor brings deep insights into AI and software engineering, enhancing the foundational knowledge of the research. Together, their combined guidance will not only ensure a comprehensive approach but also provide the student with opportunities to interact with other engineers and computer scientists, broadening their network beyond the immediate supervisory team. Depending on their background, the student may receive training in building service engineering, artificial intelligence and deep learning, and Python programming.

Supervisor: Dr Yanyi Sun

Contact Dr Yanyi Sun