UWSpace

UWSpace is the University of Waterloo’s institutional repository for the free, secure, and long-term home of research produced by faculty, students, and staff.

Depositing Theses/Dissertations or Research to UWSpace

Are you a Graduate Student depositing your thesis to UWSpace? See our Thesis Deposit Help and UWSpace Thesis FAQ pages to learn more.

Are you a Faculty or Staff member depositing research to UWSpace? See our Waterloo Research Deposit Help and Self-Archiving pages to learn more.

Photo by Waterloo staff

Communities in UWSpace

Select a community to browse its collections.

Recent Submissions

  • Thumbnail Image
    Item type: Item ,
    Deep Learning-based Identification and Change Detection of Oil/Gas Well Pads Using Satellite Imagery
    (University of Waterloo, 2026-09-22) Xu, Hongzhang
    Global energy extraction and industrial activities have caused widespread land disturbance, making large-scale and accurate environmental monitoring essential for ecosystem protection and land reclamation. Satellite remote sensing provides a powerful tool for monitoring these environmental impacts. In recent years, deep learning algorithms for remote sensing image interpretation have developed rapidly. However, significant gaps remain in bridging algorithmic developments with practical domain applications. In real-world scenarios, existing target extraction algorithms rarely consider the spatial context between targets and their surrounding environments, and optimal training constraints, such as loss functions, remain under-explored. To address these general challenges, this doctoral study develops a series of deep learning methods for target extraction, change detection, and land disturbance and reclamation evaluation, using oil/gas well pad monitoring as a primary application. The research follows a systematic progression: 1. Loss Function Optimization for Road Extraction: Linear feature (Road) extraction plays a foundational role across diverse remote sensing applications. However, how to select a suitable loss function for linear feature extraction is rarely studied. To address this, I conducted a comprehensive comparative study of 12 loss functions for road segmentation, showing that region-based loss formulations (e.g., Log-Cosh Dice and Squared Dice) significantly outperform distribution-based loss functions in maintaining the connectivity of linear features. 2. Well Pad Identification: To overcome the challenge that target extraction algorithms often ignore environmental context, I developed a modified Mask R-CNN network based on the coupled spatial relationship between roads and well pads. By incorporating the road network as a spatial prior, the proposed model effectively solves the spectral similarity problem between abandoned well pads and natural vegetation, improving average precision by over 20% compared with baseline methods. 3. Well Pad Change Detection: To evaluate post-disturbance land recovery and semantic transitions after mining development, I proposed a constrained dual-head HRNet architecture for semantic change detection. By employing a cosine similarity loss to constrain feature structures, the model achieves an 80.05% mIoU on the semantic change detection task. Moreover, to support these methodological advancements and promote benchmark evaluations, we constructed two comprehensive datasets—the Alberta Roads and Wells Dataset and the Alberta Semantic Change Detection dataset—using satellite imagery over oil sands regions in Alberta, Canada. Overall, this research advances the practical capabilities of deep learning in remote sensing by tackling foundational challenges in loss function selection, spatial context modelling, and semantic change analysis, providing a transferable and scalable methodology for broad environmental and geographic applications.
  • Thumbnail Image
    Item type: Item ,
    Development of a Soft Robotic Arm Compression Sleeve with Tangential Motion for Assisted Lymphedema Management
    (University of Waterloo, 2026-09-22) Kowalski, Jacob
    Lymphedema is a chronic condition affecting over one million Canadians, in which impaired lymphatic function reduces the body’s ability to circulate and process lymphatic fluid. Management typically requires ongoing treatment, often including Manual Lymphatic Drainage (MLD) by trained specialists. However, access to these treatments can be limited, while current at-home compression devices primarily apply normal compression rather than reproducing the directional skin deformation characteristic of MLD. Existing active compression garments can also be bulky and non-portable, and may require users to remain relatively stationary during treatment. These limitations motivate the development of alternative wearable technologies that can improve access to treatment while reducing disruption to daily activities. Soft robotics technologies offer a promising approach to addressing these limitations; however, existing wearable soft robotic systems can be constrained by the cost and bulk of pneumatic control hardware, the inability to generate controlled tangential motion along the skin, and limited options for compliant surface-pressure sensing. One contributor to system cost is the use of high-performance solenoid valves, which can cost tens to hundreds of dollars for precise pneumatic control [1], [2], [3]. In contrast, low-cost miniature on/off solenoid valves under three dollars are widely available and offer an attractive alternative for portable and affordable wearable systems [4]. However, their flow characteristics can vary significantly among valves and operating conditions, and their performance is often insufficiently characterized for direct incorporation into model-based pneumatic control. To address these challenges, this thesis contributes: (i) an experimental framework for characterizing and modelling the flow characteristics of low-cost solenoid valves, identifying their controllable operating regions, and incorporating the resulting models into closed-loop pneumatic control; (ii) a custom flat, flexible capacitive pressure sensor; (iii) a movable Pneumatic Artificial Muscle (PAM)-based compression cuff and cable-driven locomotion system; and (iv) the integration of these components into an active compression sleeve prototype. The developed active compression sleeve integrates the mechanical and pneumatic hardware required to apply compression while enabling controlled tangential motion of the cuff along the limb. The primary mechanical, pneumatic, and sensing subsystems were evaluated independently to characterize their performance and demonstrate their feasibility for integration. Full closed-loop operation of the final integrated prototype remains a subject for future work. Nevertheless, the resulting system establishes a foundation for further calibration, control development, and experimental evaluation of a wearable device intended to supplement existing approaches to lymphedema management.
  • Thumbnail Image
    Item type: Item ,
    Modeling and Characterization of a Tunable Coupler-Flux Qubit Ultrastrongly Coupled to an Open Transmission Line
    (University of Waterloo, 2026-09-22) Rafati, Parinaz
    Studies in relativistic quantum information have shown that the vacuum state of a quantum field contains pre-existing correlations. Vacuum correlations can be extracted locally by coupling spatially separated probes to a quantum field even without direct light-matter interaction. Despite extensive theoretical work, there has been no experimental demonstration of entanglement harvesting to date. A superconducting circuit design has been proposed as a platform for investigating entanglement harvesting. The device consists of a flux qubit coupled to a one-dimensional transmission line through a tunable coupler. The tunability of the coupler provides control over the qubit-field interaction, allowing the coupling strength to be tuned over a range from the weak regime to the ultrastrong coupling regime at nanosecond time scales. These features make the design a promising platform for investigating entanglement harvesting from vacuum correlations under controlled experimental conditions. However, as the system approaches the ultrastrong-coupling regime, commonly used approximations, such as the rotating-wave approximation (RWA) in the spin-boson model and the two-level approximation for the qubit, may no longer provide an accurate description of the system. In this thesis, we investigate a superconducting qubit design as a potential platform for future studies of entanglement harvesting. We first develop a theoretical model of a tunable coupler–flux qubit galvanically coupled to a transmission line and derive the Hamiltonian of the coupled system. The model is then used to calculate the transverse and longitudinal coupling strengths between the qubit and the transmission-line modes and to investigate their dependence on the coupler flux. We then characterize a proposed three-loop superconducting qubit design through numerical simulations and comparison with experimental spectroscopy data. The system is calibrated to establish the relation between the applied voltages and external fluxes. We then investigate how the junction parameters and junction asymmetry affect the agreement between the simulations and experimental data. Finally, the coupler flux is varied to study its effect on the simulated response. The comparison shows that variations in the junction parameters and junction asymmetry can improve the agreement with the experimental data, while variations in the coupler flux do not lead to a systematic improvement under the assumptions considered.
  • Thumbnail Image
    Item type: Item ,
    Investigating the relationship between staffing structures, working conditions, and quality of care in Ontario Long-Term Care Homes
    (University of Waterloo, 2026-09-22) Miller, Michaella
    Background: Chronic underfunding and increased privatization of the Canada’s long-term care (LTC) sector, coupled with an older population and increased complexity of care, has deteriorated working conditions. These conditions have created a reliance on contract work, intensified and stressful work, and decreased job satisfaction and created environments where workers are less inclined to stay at their jobs. Additionally, Ontario mandated an increase in direct care hours required for residents and intends to build more beds for older adults in need of care. These changes require additional staff to meet regulated care requirements. There is a clear need for strategies to recruit and retain a strong LTC workforce and to address retention by improving working conditions. Methods: This thesis sought to explore the relationships between quality of care, working conditions, and staffing practices in LTC through a narrative scoping review, an analysis of staffing data and resident care outcomes, and a qualitative analysis exploring the work experiences of staff and how staffing practices affect care and work. Results: The narrative scoping review (Chapter 2) investigated the contextual factors affecting staffing decisions and the impacts of staffing structures on direct care workers' quality of work-life and work-related outcomes. Contextual factors included market-based ideologies, increased care complexity, regulatory requirements, the impact of COVID-19 and organizational fiscal austerity. Generally, these factors reduced the number and skill mix of staff prior to the COVID-19 pandemic and negatively impacted the quality of work-life and work outcomes, such as reducing job satisfaction and increasing burnout. When homes relied on lean staffing models to save on costs, staff compensated by absorbing the negative impacts of fewer staff by working unpaid overtime and finding workarounds. Chapter 3 examined how PSW staffing patterns were associated with resident care quality outcomes in LTC. The regression analysis of the relationship between PSW staffing and resident quality of care composite score did not find any statistically significant relationships. The lack of relationships in Chapter 3 may be further explained, in part, by the qualitative exploration of staffing in LTC (Chapter 4). This study explored the LTC work environment and staff perceptions of how staffing is organized insofar as it affects their ability to provide care and have a healthy working environment. The qualitative analysis found that the addition of PSWs, as per mandated hours of care regulation, improved workloads for PSWs. However, quality of employees was as important as the quantity of employees. Disruption in team dynamics and distressed care markets may have resulted in a lower quality workforce. In addition, those in supervisory positions in LTC have a workload that has quietly changed and increased in scope but remained unmonitored, resulting in those with the most responsibility in LTC homes struggling with their workloads. Staffing in the LTC organization were not allocated based on care acuity, which impacted whether appropriate care personnel were available for different care requirements and created inequitable workloads between care units in the homes. Conclusions: With the growing demand for LTC globally, there will be a need to train, hire, and employ more care workers. To ensure that the care received by residents is of high quality, sustainable systems will need to be upheld and established that address the conditions of care, including work organization and staffing allocation appropriate to the care needs, education standards that promote well trained hiring pools, appropriate recognition of the time allocated for additional roles and responsibilities, and regulation that addresses skill mix disparities.
  • Thumbnail Image
    Item type: Item ,
    Safe, Adaptive, and Scalable AI-Driven Energy Management of Urban Multi-Energy Systems
    (University of Waterloo, 2026-09-22) Kenawy, Ahmed Shaban Omar
    Cities serve as central hubs of economic, industrial, and social activity across nations. However, the high population densities, essential infrastructure networks, and diverse industrial operations position cities as the largest energy consumers and the primary contributors to greenhouse gas (GHG) emissions. This poses critical energy and environmental challenges on the urban scale. These challenges include the need to enhance energy generation and consumption efficiency and to achieve a substantial reduction in GHG emissions across different energy sectors. One promising solution is the transition from the traditional, independent planning and operation of energy sectors to the integrated planning and operation of Urban Multi-Energy Systems (UMESs). In this context, a UMES can be defined as a city-scale energy system that coordinates electricity, natural gas, heating, cooling, and other energy sectors as a single integrated system. This integration begins at the multi-energy buildings level, expands to community-level Multi-Energy Microgrids (MEMGs), and ultimately forms city-scale Networked Multi-Energy Microgrids (N-MEMGs) connected through electricity, gas, and heat distribution networks. By coordinating multiple energy carriers, UMESs can facilitate integration of variable renewable energy, improve overall energy efficiency, and enhance operational flexibility and resilience. Despite these advantages, energy management of UMESs is a particularly challenging operational problem. This is due to complex multi-energy flows, uncertainty propagation, decentralized ownership, privacy limitations, and the need for emission-aware operation. In this context, the energy management of UMESs has been addressed using two distinct approaches: model-driven and AI-driven. Model-driven approaches can explicitly represent physical constraints and yield interpretable solutions; however, they often suffer from high computational complexity and rely on complex mathematical optimization models, thereby limiting their suitability for real-time applications. On the other hand, AI-driven approaches offer adaptive decision-making capabilities under uncertainty. Among these approaches, Deep Reinforcement Learning (DRL), which formulates sequential optimization problems as Markov Decision Processes (MDPs), has gained significant attention. However, conventional DRL methods lack explicit mechanisms to enforce physical constraints, thereby limiting their applicability to real-world energy management systems. The primary objective of this thesis is to develop a safe, adaptive, and scalable AI-based energy management framework for UMESs. The proposed framework models the system as a Constrained Markov Decision Process (CMDP) and employs Constrained Deep Reinforcement Learning (CDRL) algorithms to solve it. The framework aims to generate low-carbon and economically efficient dispatch strategies while adhering to the operational and engineering constraints inherent in physical multi-energy networks. Additionally, it accounts for uncertainties related to renewable energy resources, energy prices, and energy demand. The first part of the thesis addresses the energy management problem of single MEMG systems through a hierarchical two-layer framework. In the first layer, a model-driven Mixed-Integer Quadratic Programming (MIQP) formulation performs day-ahead scheduling by minimizing operational costs subject to the relevant system constraints. In the second layer, a CDRL agent performs real-time adjustments to compensate for uncertainty and operational deviations. This framework combines the strength of CDRL in sequential decision-making under stochastic conditions with the structural and feasibility guarantees offered by model-driven mathematical programming. In this way, the day-ahead optimization layer guides the agent’s exploration during training and reduces reliance on black-box policies during real-time operation. Although the model-driven day-ahead layer developed in the first part provides valuable guidance for the CDRL agent’s decisions, it becomes computationally expensive as system complexity increases. Therefore, the second part of the thesis eliminates this dependence and solves the energy management problem for a single MEMG using a fully model-free CDRL approach. This approach incorporates an integrated demand response (IDR) strategy that jointly exploits demand-side flexibility across electricity, heat, and gas, and it models carbon capture, storage, and utilization (CCSU) facilities that enable participation in carbon trading markets (CTMs). The operational dynamics of the system are formulated as CMDP and solved using the interior-point policy optimization (IPO) algorithm. The proposed framework yields dispatch decisions that improve both economic and environmental performance while ensuring satisfaction of system constraints. The final part of the thesis extends the approach to cooperative energy management of networked MEMG systems using a Constrained Multi-Agent DRL (CMADRL) method. Here, the problem is formulated as a constrained Decentralized Partially Observable Markov Decision Process (Dec-POMDP). This jointly captures the interactions between each MEMG operator and the energy network operators, such as power, gas, and heat. The Dec-POMDP balances a cooperative economic-emission objective with physical network constraints. This formulation explicitly accounts for both the internal distributed generators (DGs) within each MEMG and the cross-network coupling DGs. It further defines the necessary components for multi-agent training, including decentralized observations, agent-specific action spaces, and a cooperative reward. In addition, a novel Sensitivity-Weighted Constraint Decomposition (SWCD) mechanism, derived from network sensitivities, is developed to compute per-agent physics-informed constraint-cost signals, enabling the training of multiple agents for safe and cooperative dispatch. CMADRL is trained using the HeterogeneousAgent Proximal Policy Optimization-Lagrangian (HAPPO-Lag) algorithm. The resulting physics-informed framework enforces constraints across the coupled power, gas, and heat distribution networks in a decentralized and privacy-preserving manner. Collectively, these three contributions establish a unified, safe, adaptive, and scalable AI-driven framework that progresses from single MEMG to city-scale networked multienergy systems. The proposed methods deliver low-carbon, economically efficient energy dispatch while ensuring compliance with the physical and engineering constraints governing coupled power, gas, and heat networks. The framework thus offers a practical pathway toward the real-time, privacy-preserving, and emission-aware energy management of future urban multi-energy systems.