As the energy transition accelerates, improving wind energy efficiency and forecasting becomes increasingly critical. One key challenge lies in reconstructing high-fidelity atmospheric boundary layer (ABL) flow fields from sparse measurements, especially in regions influenced by wind turbines. This thesis explores the use of Latent Diffusion Models (LDMs) to reconstruct physically plausible ABL flow fields from limited spatial data. Where previous work focused on homogeneous, neutral ABL states, this research extends the methodology to more diverse and realistic conditions by including both stable and neutral boundary layers with embedded wind farms. A conditional diffusion model is trained in the latent space of an autoencoder (AE), using both local measurements and global atmospheric labels. The model is evaluated using statistical, physical, and spectral metrics, and its ability to generalize across multiple ABL regimes is analyzed. Results show that the model can generate realistic reconstructions from extremely sparse inputs, including turbine wake structures, and can potentially serve as a tool for initializing Large Eddy Simulations (LES). These findings mark an important step toward integrating generative models into operational wind forecasting and control systems.

This research investigates the effectiveness of graph-based data augmentation techniques in improving the performance of DG4b, a deep learning model designed to estimate bicycle travel times in urban environments. Given the limitations of real-world cycling datasets, particularly data scarcity and trip-length imbalance, we propose two augmentation methods: Graph Stitching (GS), which combines segments of existing trips to form new trajectories, and Graphon-Inspired Trip Generation (GITG), which uses an empirically estimated transition kernel to simulate realistic trip patterns through probabilistic sampling.
Despite limited improvements, this study establishes a foundation for future research in graph-based trajectory augmentation. Integrating richer trip-level features, such as dynamic environmental conditions or behavioral data, with structural augmentation could lead to more effective training data and improved model generalization.

Estimating bike trip times is becoming more and more important in many different areas such as urban mobility and route planning. However, especially in real-world, the GPS data used to generate these estimations is frequently noisy, irregularly sampled, or incomplete. With an emphasis on how these strategies interact with trip length and speed variance, this study intends to examine the effects of various data resampling techniques on the precision of bicycle travel time estimations. To analyze the impact of different preprocessing methods, we apply and assess a graph neural network model using various resampling techniques. Instinctively, the assumption that we expect to be concluded from this research is that there is no single resampling technique works well for every kind of trip. Rather, trip parameters like duration and speed fluctuation have a significant impact on accuracy.

Accurate estimation of bicycle trip travel times remains a challenge due to the limited availability of structured cycling data. This paper investigates how graph-based data augmentation can be used to address this limitation, specifically within the context of the DG4B model, a Graph Convolutional Neural Network for travel time estimation. We explore and evaluate three augmentation techniques: Random Walk (with and without node revisiting), Dijkstra Walk and Subgraph Stitching. These methods generate new trips by traversing or recombining paths within an existing road network graph, aiming to expand the training dataset while preserving realistic routing behavior. The augmented data is evaluated both statistically, using metrics like mean, variance and Frobenius norm, and in terms of model performance using RMSE, MAE and MAPE. Experimental results show that Subgraph Stitching and Dijkstra Walk yield the most effective improvements in model accuracy, with each method exhibiting strengths across different trip duration ranges. This work demonstrates that carefully designed graph-based data augmentation can improve GCNN-based travel time predictions in settings with limited cycling trip data.

Natural disasters frequently cause casualties and property losses. Predicting and mitigating the impact of such threats is crucial to the work of humanitarian organizations. The interactions between hazards are best represented through a multi-hazard approach, and machine learning models are well suited for natural hazard prediction. This study presents a systematized literature survey of machine learning in multi-hazard disaster forecasting in the years 2019-2025, focusing on the used models and performance metrics, their applications and feasibility of use, as well as potential cross-applications. There is a wide variety of models and metrics used. The most commonly used models are random forest and support vector machine and the most prevalent performance metric is the ROC-AUC score. The machine learning models generally perform well, with AUC scores above 0.8, though patterns in performance are difficult to examine. Feasibility is defined here as readiness to be used in practice, and the models are rated in the factors that define it. Most of the articles are feasible. Consideration of cross-application is rare and should be extended. This research summarizes the main trends in the field of disaster forecasting, providing a clear reference point for other academics.

Displacement is a focal point of humanitarian aid efforts, since it affects millions of people globally. Mitigating the consequences of forced migration is important for reducing suffering and one way of doing so is through predicting displacement to prioritise resources in advance. To achieve this, machine learning can be used for its ability to analyse larger amounts of data and identify latent structures more efficiently than human experts. Through a systematized literature review, this research evaluates thoroughly six machine learning tools: UNHCR's Jetson, DRC's Foresight and AHEAD, the EU's EUMigraTool and EPS-Forecasting, and the agent-based simulation Flee, in order to assess their suitability to that end. The analysis compares these tools across several criteria, including the way they use data, algorithmic characteristics, and operational use cases. Finally, it makes recommendations about what should be considered and how to choose amongst the tools for displacement prediction.

As humanitarian needs increase while donor budgets decrease, anticipatory strategies are essential for effective crisis response. In this context, machine learning (ML) has emerged as a promising tool for crisis forecasting, offering the potential to support timely interventions and humanitarian decision-making. However, despite rapid developments in ML-based prediction models, questions remain about their practical utility and trustworthiness in real-world humanitarian settings. This study presents a systematic scoping review of 32 academic and gray literature sources to assess the reliability and feasibility of ML systems for conflict forecasting. By analyzing these systems across dimensions such as forecasting scope, data sources, modeling approaches, validation practices, and ethical considerations, the study finds that while some models demonstrate strong predictive performance and methodological rigor, many lack transparent validation, robust error analysis, and operational applicability. The review concludes that while ML systems hold substantial potential for enhancing conflict anticipation, their current real-world readiness is uneven and context-dependent.

With the worsening of climate change, the complications brought on by floods every year create an increasing need for forecasting systems that humanitarian organizations can use to help populations in danger. This research presents a literature review of machine-learning models for impact-based flood forecasting, and compares them with existing humanitarian projects. The results examine the characteristics of the models surveyed, while the discussion focuses on understanding how these characteristics can define whether the machine learning models proposed can actually be translated to humanitarian settings. The main takeaways include the prevalent choice of deep learning and ensemble models, used to improve the adaptability of the models, the problems with data availability and data quality in different areas considered, and the difference between lead times, usability, and scalability of the models proposed in contrast with already used humanitarian projects. This study then highlights the importance of transparency and reproducibility of the survey by detailing the queries and databases used, ensuring accessibility of selected articles, and explaining the selection criteria and methodology. Ultimately, the review concludes with the key insights on the connection between academic prototypes and real-life humanitarian projects, as well as key areas for future research.

The combination of increasing global food demand with increased food security risks associated with climate change amid a decreasing number of skilled growers necessitates innovative solutions in green- house horticulture. Autonomous growing offers a solution based on greenhouse climate forecasting and (optimal) control. However, current theoretical models developed for greenhouse climate forecast- ing face limitations due to the in-depth physics knowledge required for their use and their dependence on intricate system parameters that are difficult to estimate. Conversely, machine learning models struggle with generalisation to unseen conditions and adherence to physical laws, leading to unrealis- tic predictions in greenhouse environments. This study addresses these challenges by exploring the use of Physics-Informed Machine Learning (PIML) techniques to enhance greenhouse climate fore- casting. A simple differentiable theoretical model for simulating the greenhouse climate is proposed to serve as prior physical knowledge of the system. Subsequently, a novel PIML model is introduced in the form of Controlled Aphynity (CA), which integrates insights from neural controlled differential equations and Aphynity, and is the first such model that allows for the augmentation of incomplete prior knowledge of a dynamical system with data-driven machine learning models while being adaptable to changing dynamics due to forces acting on the system. Experimental results show that CA is capable of successfully augmenting incorrect physics under changing dynamics on the task of humidity deficit prediction in the greenhouse. Furthermore, three ensemble methods combining CA with traditional ma- chine learning techniques are explored and demonstrate promising synergies. A detailed case study evaluates CA and the best-performing ensemble approach on the task of humidity deficit prediction under realistic greenhouse scenarios over a complete crop cycle. Both CA and the ensemble methods exhibit superior adherence to physical laws, lower data requirements, and improved performance on outliers compared to conventional machine learning methods. This research contributes to advancing greenhouse climate modelling, underscoring PIML’s potential in optimising the greenhouse climate.F

Unlike traditional blur filters, the bilateral filter exhibits non-linear blur behaviour as its kernel size increases. This atypical blur behaviour makes it challenging to find a good σr . This paper investigates the underlying reasons for this behaviour and proposes methods to align the bilateral filter’s blur scaling linearly with its spatial filter size. Using local frequency analyses to quantify blur levels, we introduce an approach that finds the best σr through iterative search. Results demonstrate that the pro- posed method effectively counters the atypical blur behaviour. However, the proposed method does not perform sufficiently when handling very large kernel sizes. The proposed method can be used to abstract away the σr parameter when seeking linear blur behaviour in the bilateral filter. Further re- search is needed to make it functional for very large kernel sizes.

The bilateral filter is a popular filter in image processing and computer vision. This comes from the fact that it is able to blur images while keeping the structure intact. However, the bilateral filter allows for blurring to happen across edges. This can result in halo-like effects around the edges of structures if both sides are made up of different intensities. In this paper, we propose an extension to the bilateral filter that reduces this phenomenon of blurring across edges. By giving the filter knowledge of the edges beforehand, it is possible to prevent the filter from blurring past them. When we filter a pixel, its surrounding area within the kernel is checked for edges. If a pixel within this area lies on or beyond an edge, its weight for blurring is reduced. As a consequence, pixels that lie past an edge have less influence on blurring. We show that this new edge-aware bilateral filter reduces across-edge blurring compared to the standard bilateral filter. Furthermore, when we allow a bigger range of intensities to mix, the new filter is also able to prevent the filtered image from appearing washed out, unlike the bilateral filter.

The bilateral filter is an edge-aware image filter. While it has a variety of applications, its naive implementation is quadratic in nature, hindering the ability to efficiently process multi-megapixel images. If performance is needed, like in a real-time setting, an approximation is necessary. Current literature on Fourier series-based approximations does not explore the capabilities of graphics processing units (GPUs) as viable platforms for this computational problem. This paper proposes an approach for implementing such filtering on a GPU by conducting a series of separable convolutions, and also investigates the use of different range kernels. Our adaption of the bilateral filter is found to be more two times faster than readily available solutions, with frame times showing that real-time performance is possible for large spatial kernel sizes and image resolutions.

Traditional bilateral filters, effective in 2D image processing, often fail to account for the 3D structure of meshes, leading to artifacts in texture filtering. This thesis introduces On-Mesh Bilateral Filtering, a novel method that adapts the bilateral filter to work with non-contiguous texture mappings by incorporating 3D spatial distances and face adjacency information into the filtering process. The On-Mesh Bilateral Filter combines mesh surface sampling techniques with heat geodesic distance calculations to create a geometry-aware kernel that achieves more accurate and context-sensitive smoothing operations, respecting both the mesh topology and texture space properties. This paper hopes to encourage further research in the area of geometry-aware texture filters.

This paper introduces the Quadrilateral filter, an advanced extension of the Bilateral and Trilateral filters aimed at addressing limitations in high-gradient regions of images. While the Bilateral filter effectively preserves edges during smoothing, it struggles with intensity variations, leading to blunted image details. The trilateral filter improves upon this by incorporating local plane geometry approximations but assumes linear pixel intensity distributions, limiting its effectiveness. The proposed Quadrilateral filter utilizes curvature-based geometry approximations to enhance noise reduction, contrast preservation, artifact reduction, and image reconstruction by accounting for nonlinear pixel value distributions. The development of this filter represents the main contribution of the paper while exploring whether the established Bilateral and Trilateral filters’ performance can be further improved through curvature-based local geometry approximations. The findings demonstrate improvements in image quality and detail preservation, with broad implications for applications in image de-noising, tone-mapping, multimedia processing, and beyond.

Solutions for the Train Unit Shunting Problem are constantly being researched and improved to be- come more efficient and match the needs of train transport in the Netherlands. For this reason, we are exploring new ways to find patterns in the train data to identify where those solutions could be en- hanced. More specifically, we are trying to find patterns that make identifying different locations possible. We identify patterns in the capacity of the shunting yards and the types of trains used in various locations, which result in reasonable ac- curacy in classification. Some locations operate closer to their capacity, and some require longer paths to get inside the shunting yards. These find- ings could be helpful not only for the planning algo- rithms but also in identifying which locations might need expansion or restructuring and where more of the train fleet should be allocated.

Shunting yards are locations next to train stations that serve as parking places for trains when they are not in operation and often contain facilities for maintenance and cleaning for passenger trains. Planning of the tasks regarding shunting trains involves routing, assignment of tracks, and scheduling tasks. This is done manually and requires a lot of effort, making it inefficient. Identifying patterns specific in the arrival times of trains at shunting yards can help to predict future train arrivals and potential delays throughout the year more accurately. This enables the alignment of staff and equipment with train arrivals, minimizing idle time and optimizing cost efficiency.
This research focuses on extracting and analyzing the arrival times of trains at shunting yards using a dataset consisting of GPS data. It conducts two algorithms to cluster the given data for each train unit within and across days to identify the same train across different days. Distributions and heatmaps of the arrival times and delays are created based on the identified train series. They are analyzed to identify patterns in train arrival times and delays across different months.

This paper analyses manually realised solutions to the Train Unit Shunting Problem (TUSP) to find patterns in train type. The parking element is most important for the TUSP. Therefore, this research specifically investigates the presence of train type patterns in parking track and parking time. The difference in the patterns between main train type and train subtype is also analysed. The study uses statistical hypothesis testing to look for biases between individual train types and parking tracks. Kernel density estimation is used to analyse the differences in parking time between the types. The results show that there are strong patterns in type and parking track, but no clear difference in parking time. Considering subtype results in the differences being more specific. It is suspected that the strongly present track pattern is a strategy used by human planners.

When not in service, trains are parked and serviced at shunting yards. The Train Unit Shunting Problem (TUSP), an NP-hard problem, encompasses the challenge of planning movements and tasks in shunting yards. A feasible shunting plan serves as a solution to the TUSP. Current automated planning tools utilized to assist human planners in this computationally heavy planning task are not able to distinguish inherent patterns in input train data, as opposed to humans. This paper aims to address this technological gap by examining whether valuable patterns could be extracted from shunting plan data, consisting of solutions to the TUSP. More specifically, it is mainly concerned with the automatic detection of whether a solution to the TUSP is a week or a weekend day. Therefore, the data is examined for the presence of several groups of patterns. Moreover, binary classification is performed on the data. The experiments conducted in this study suggest the presence of valuable patterns in the data, which could be leveraged to design specialized heuristics for automated planning models tailored to generate shunting plans for weekdays and weekends.

This research aims to find patterns in the live position data of trains within shunting yards. These patterns can be converted to heuristics and applied in algorithms developed by railway operators in the Netherlands to tackle the Train Unit Shunting Problem. The usage patterns were extracted from real-world location data of train units. Specifically, this research focuses on finding patterns in the paths taken in both temporal and spatial metrics. These investigations identified the busiest times in the shunting yards according to various metrics, such as the total number of trains and the number of serviced trains. These metrics are extracted from the type of train movement at a given moment, which was provided with the dataset. The accuracy of the provided train movement category has been analyzed and shown to be inaccurate for uses within shunting yards compared to a proposed approach. Finally, an algorithm for classifying train units that belong to the same train has been shown to have initial success.