In this thesis we present a new idea to objectively assess reconstruction algorithms. Because it is not feasible to completely scan a high-detailed ground truth mesh of large urban objects, the performance of the reconstructed meshes can therefore not be measured objectively. To solve this, we present a new mesh evaluation methodology that can more objectively assess the quality of the generated mesh based on a low detailed ground truth mesh. We achieved this by creating a synthetic dataset based on low-detailed models of large urban buildings and using this as a ground truth mesh and input data for the reconstruction algorithms. Thanks to our new methodology, we were able to compare the output mesh and ground truth mesh using a wireframe model of the meshes. This allows us to give a more objective score to the results without having to look at entire model, which is the usual method. The results of this thesis show that the new methodology has potential to be used for creating a new benchmark, and it opens a new door to using more readily available objects that could not be used before.

Computation Fluid Dynamics (CFD) simulations are used in a diverse set of fields such as aerodynamics, automotive, biomedical engineering and wind impact. With the advancements in technology the scale of these simulations has increased significantly. This has resulted in \textit{massive} CFD simulations --- simulations that do not fully fit within RAM. Due to the limitations in RAM, visualizing the results of \textit{massive} CFD simulations has become an issue, mainly on personal computers. Existing solutions necessitate either substantial external servers equipped with sufficient RAM, a costly and inefficient approach that struggles to accommodate increasingly larger CFD simulations, or reliance on manual intervention for data loading and unloading. However, manual intervention introduces potential for error.

This thesis proposes a solution to automatically load/unload data from memory based on real-time demand. To achieve the proposed solution the methodology is split into two main stages: \textbf{(a)} pre-processing and \textbf{(b)} visualization.

The pre-processing is required to efficiently manage the \textit{massive} amount of data during the visualization step. It involves segmenting the study area into smaller, more manageable regions. Furthermore, it generates multiple level of details for each region such that the desired level of detail can be used as required.

The visualization is performed within game engines --- Unity for this thesis. Game engines provide a solid starting platform as they include aspects such as read/write operations, rendering capabilities, and flexible code execution. During visualization, the relevant regions --- regions that are within the user's point of view --- are automatically loaded into memory. subsequently, regions that leave the user's point of view are automatically loaded out of memory. Utilizing iso-surfaces, volume rendering, and barbs, the loaded data is then presented to the user.

The results showcase that visualizing \textit{massive} CFD results within game engines is possible in real-time. However, through the data transformation performed in the pre-processing step the data has lost some accuracy. Thankfully, an downward trend can be seen in the loss of accuracy as the level of detail increases. The result show that for data used in the thesis the pre-processing takes between 390 seconds (6 minutes and 30 seconds) and 972 seconds (16 minutes and 12 seconds). Furthermore, a data size reduction of up to 84\% can be seen after the pre-processing has finished.

Computational Fluid Dynamics (CFD) simulations for residential areas are becoming increasingly important as the urban population keeps growing and extreme weather conditions due to climate change are becoming more prevalent. Since CFD simulations simulate and visualise fluid flows, users can analyse and predict air flows in urban environments, giving insight in pollution, heat dissipation, and weather conditions. Performing these simulations demands expertise and time: 3D urban models must be prepared, and pre-run setups must be defined to obtain accurate results. Partial automation can streamline this process. Therefore, we developed a method that identifies geometric errors and defines mesh parameters for the open source CFD software OpenFOAM. This method follows the ISO19107 standard and recent CFD guidelines for urban areas, ensuring accurate simulation results. We validated algorithms with a variety of urban models and parameters, and analysed the workflow developed for the mesh parameters definition. Additionally, we created a prototype, in the form of a web application, in which these algorithms are implemented. Our prototype will simplify the use of CFD simulations for urban areas, making them more accessible to everyone.

Digital Surface Models (DSMs) are commonly employed to investigate topographical characteristics and processes; however, the presence of canopy and infrastructure in urban and forested areas can lead to height biases and inaccuracies. In this study, I aim to correct such biases by applying a deep learning approach known as Residual U-Net to remove the selected pixels and generate Digital Terrain Models (DTMs) that accurately represent the Earth's surface without canopy and infrastructure influence.

The Residual U-Net model was trained and tested on a dataset of DSM and DTM pairs, which were acquired from resampled AHN4. The model was evaluated on its ability to predict DTMs from DSMs, and its performance was compared with other existing methods. Additionally, the model was tested on different resolutions and the Copernicus DEM to assess its adaptability and generalization capabilities.

The results indicate that the Residual U-Net model outperforms conventional techniques, effectively reducing the influence of canopy and infrastructure, and resulting in DTMs with enhanced precision. The study also explores the errors in detail and identifies the model's error causes, highlighting its limitations and areas for potential improvement.

This study concludes by demonstrating the efficacy of applying deep learning techniques, such as Residual U-Net, to correct global elevation models for canopy and infrastructure. The results indicate that the model is a promising tool for topographical investigation in both urban and woodland situations, offering a versatile solution for generating accurate DTMs from DSMs.

With the increasing pressure on global forests due to deforestation and habitat loss, it is more important than ever to understand our forest ecosystems on a larger scale. Canopy gap fraction is an indicator used for estimating forest biomass and better understanding of ecosystem functioning. For decades there have been research on computing canopy gap fraction using ground measurements as well as Airborne Laser Scanning (ALS). These approaches, however, are limited by the data available. A global coverage of data on canopy gap fraction could be made available by space-based laser altimetry mission Ice, Cloud and land Elevation Satellite (ICESat-2). Although its main scientific objectives are focused on polar areas, it has already proven to facilitate broader scientific disciplines. The ATL08 data product is focused on land-vegetation and already provides global data on canopy heights. However, there is ongoing research for using ATL08 data for canopy gap fraction estimation. Although some approaches have been suggested in the literature, a tested workflow to achieve this goal has not been published.

This thesis tests two methods for estimating canopy gap fraction from ICESat-2 ATL08 data and evaluates the results against openly available ALS data. First, a simple method of using canopy to total photon ratio is used. Then, an alternative method that aims to correct for the surface reflectivity is tested. The results from both methods are similar, therefore the computationally less expensive method is recommended. Although this thesis does not achieve to present a sufficiently accurate approach for using ICESat-2 ATL08 data for canopy structure estimation, it is shown that further research is needed and the results are promising. Furthermore, it is demonstrated that annual trends in canopy gap fraction can be seen in ATL08 data. Considering the global coverage of ICESat-2 data, it is concluded that despite the accuracy not meeting the expectations, using ATL08 for studying canopy gap fraction on a global scale and through time has high value and great potential for environmental research.

This thesis introduces a Learned-Based Multi-View Semantic Stereo method, addressing the limitations of traditional and learned-based Multi-View Stereo (MVS) techniques in reconstructing reflective and low-textured regions, particularly prevalent in 3D models of buildings. Traditional methods lack completeness, while learned-based methods struggle with accuracy. Focusing on enhancing 3D models of buildings, this research integrates semantic information into the existing deep learning architecture for depth prediction, specifically CasMVSNet, to guide the reconstruction process. Three key strategies are employed: first, the incorporation of semantic maps into the network through a multi-modal approach; second, the introduction of a multi-modal refinement module at the end of the CasMVSNet model to improve the initial output depth maps; and third, the introduction of two new loss terms designed to enforce varying degrees of smoothness on specific semantic categories. Experimental results, conducted on the DTU dataset, demonstrate a significant enhancement in accuracy at the point cloud level while maintaining the completeness of the reconstructed models. Validation and generalization on the ETH3D dataset show consistent patterns. This research showcases the potential of integrating semantic guidance in 3D reconstruction of buildings, advancing the field of computer vision.

To keep the Panama Canal operational year round, the water level in the canal is maintained above the minimum depth. As water is passed through the locks and into the oceans on either side, the canals main reservoir looses fresh water, and this water is then replaced by the canals secondary reservoir which is Lake Alajuela. The Lake Alajuela reservoir is supplied of water by two large rivers, bringing in a sediment flux and decreasing the reservoirs capacity over time. Sedimentation sets a time limit to the use of the reservoir, and understanding this process and predicting the future morphological changes to occur in the reservoir are key to ensure continuation of operations in the Panama Canal. To predict the quantities of local sedimentation in the reservoir, a machine learning model is trained with features extracted from bathymetric models covering various years. These features are computed values that correlate with morphological processes. As such, the adaptiveness of a machine learning model along with the ability to extract morphological features from any elevation model provides the possibility to predict future sedimentation where other methods with empirical and numerical methods do not suffice due to a lack of data and restrictive parameters. Three types of machine learning algorithms and 21 features were initially tested for the purpose of the morphological modelling, during which the SVR model was the most successful. The testing was done on the R´ıo Chagres basin as well as the R´ıo Pequen´ı basin, both located in Lake Alajuela. Extensive hyperparameter tests were done to optimize and further test the performance of the SVR. Depending on the study area and the scale of the morphological behavior occurring, slightly different sets of features were most effective. Nevertheless, in both study areas tested the runoff model has proven to be a key factor for predicting the sedimentation and achieved a 70 to 80% accuracy for predicting zones of low or high sedimentation. The same model trained with the data from 1997 to 2018 was then used to predict 6 years into the future where more dynamic morphological behavior will occur according to the model. A downstream moving sediment front in the R´ıo Chagres basin is recognized and predicted to have moved 500 meters between the years 2018 and 2024. Such a sediment front travelling too far into the reservoir could have catastrophic consequences for all operations of the Panama Canal, making the awareness and anticipation of its progression highly important.

Urban physics is a multi-scale and interdisciplinary field, that combines science and engineering for the study of physical processes in urban areas. Computational Fluid Dynamics (CFD) is considered a powerful tool for the study of these processes. In the context of microscale phenomena these processes refer to the transfer of heat and mass in the indoor and outdoor urban environment, and can be observed up to ≈1km above the surface of the Earth. Their development takes place inside the Atmospheric Boundary Layer (ABL), which for the case of urban areas is referred to as the Urban Boundary Layer (UBL), and is formed due to the interactions between the surface obstacles and the wind flows. In CFD simulations the surface of the Earth and the encountered obstacles are represented with the use of 3D models, as well as estimated values that are used to implicitly represent their roughness. In this thesis the aim is to investigate relevant to CFD parameters that could be used as 3D model semantics. For this purpose, a list of parameters was identified. From this list roughness length was selected and a methodology was developed for the assignment of roughness values for the open-source software OpenFOAM. The developed methodology that was built using built-in functions of OpenFOAM, is based on an octree data structure that is used to store the input triangulated model in obj format. The roughness length landuse names are stored in an mtl file that complements the input obj and the roughness length values are specified as a user defined parameter using the landuse names. The process is semi-automated and it entails the assignment of non-uniform roughness at the bottom of the computational domain. Additionally, a methodology to assign non-uniform roughness at the inlet of the domain was developed. The results showed that the assignment of non-uniform roughness at the bottom of the domain was successful for cases of flat terrain, however, under the restriction that the input geometry model abided by certain geometry guidelines, such as no self-intersections, no gaps. For the case of non-uniform roughness at the inlet the process also produced satisfactory results in terms of the assignment process, however the impact of multiple roughness values at the inlet on the calculated flow parameters requires further investigation.

Climate change, and the effect it has on our lives and the world, has been at the centre of debate in the past decades. Also in architecture and urban planning fields, the effect of climate on buildings and cities has always had a role in the design process, nowadays especially when it comes to sustainability related topics. An interesting element within climate is the microclimate, which is a small area where climate circumstances are different then in the surrounding area. For example in an urban area the temperature difference between an area in a big city and the rural area around it can be up to 10°C, due to influences of surrounding buildings and materials. In the design process often more general weather data is used in calculation, this while they can differ a lot from reality. Modern tools make it possible to simulate the microclimate. One of these tools is ENVI-met. However, inputting 3D models into this software is mostly a manual process. This while a lot of information that is necessary is already available in existing architectural and urban design models. There is just no way to input this information into the software.

In this research a method is developed for combining detailed information from BIM models (IFC), with information about the surroundings from 3D City models (CityGML), and translating them to the ENVI-met format, so that these models can be used as input models for microclimate simulation in ENVI-met. This is done by creating a command line tool that extracts the necessary data from both input files, combining and converting it, and then writing it to a file in the ENVI-met format. Also guidelines and requirements for the input files will be established.

This is done by first establishing what information is necessary for microclimate simulation in ENVI-met and how this information needs to be represented, and then finding out where this information can be found in the intended input files, and how it is represented in there. From this can be concluded what information can be taken from which input file and the characteristics that are necessary for their correct use in the process can be established. Then the conversion tool itself can be developed, where the data is transformed to the same coordinate system and format, so that it can be combined and written to the ENVI-met format. In the last step the results are checked by doing a small case study and running the microclimate simulation.

This way, IFC and CityGML models can be used as input for microclimate simulation software ENVI-met, by using the conversion tool developed for this research and the provided guidelines.

Everything around us is rapidly changing. Whole new blocks of buildings are built, huge infrastructural projects are constructed and so on. Hence, there is a need of a reliable and up-to-date inventory of the area and the objects of interest for mapping and monitoring assets and their changes. An answer of this upcoming need is an automated inventory of infrastructure using Remote Sensing and artificial intelligence (AI) techniques. Rail sector shares the same need for fast and reliable inspection on its infrastructure. Monitoring frequently the condition of the railway infrastructure can improve the maintenance efficiency and the avoidance of hazards. The traditional monitoring techniques are costly, time consuming and in some cases dangerous, due to their reliance on the physical presence of the inspector. Hence, new state-of-the-art techniques that are able to frequently and without putting in risk human lives, inspect the condition of the railway and its infrastructure. This master thesis aims at developing an efficient workflow for combining 2D imagery and 3D light detection and ranging (LiDAR) point clouds for the automated detection and localization of the railroad infrastructural objects into 3D world coordinate system, for monitoring the railway infrastructure. Using deep learning (DL) methods in imagery we detected and mapped, approximately the 60% of the railroad equipment of our interest (i.e. light signals and equipment boxes). These detected equipment were analyzed with stereoscopic techniques to retrieve their position in 3D world coordinate system. That led to the automated creation of a geographical information system (GIS) map having the positional and class information of railway equipment. Once the detected objects were mapped, then the point cloud data were automatically cropped into voxels including the same objects. Hence, using various sophisticated machine learning (ML) techniques, the points referring to the objects were classified. Furthermore, combining the positional information provided via 2D analysis with 3D point clouds, the vertical position was refined and the height of the mapped objects was estimated. Lastly, the positional information estimated from the 2D analysis enhanced the unsupervised ML classification in point clouds. The product of this classification, has the potential to be used as training data to train supervised point cloud classifiers.

The environmental pressure on the planet and its limited capacities has resulted in the need for new building methodologies that respect this limited capacity. Building methods based on the principles of the Circular Economy could pose an answer to this problem. However, limited knowledge and tools are available to bring this into practice. This research focuses on circular building from the perspective of re-using building components upfront and its relation with the project management of non-residential building projects in The Netherlands. The study aims to clarify the role of the project management and obtain more insight into the briefing, the project organization, and the selection of the project team, in relation to the re-use of building components. By conducting qualitative research, consisting of a literature study and empirical research, including multiple expert interviews with people involved in re-use projects and case study of a renovation and a newly built office project, a better understanding has been achieved. The research suggests that the management of the initiation phase is of great importance in setting a good starting point for re-use projects. The briefing could help in this by defining clear ambitions and goals. These can guide the team throughout the process. Besides, the way projects are organized could facilitate the inclusion of re-use. This includes the extension of the initiation phase, in which an inventory of reclaimed components is started. Throughout the process better integration between activities is needed to align the reclaimed components with the design, this comes with additional iteration. Lastly, the project team selection is found to have an impact on re-use. The composition of an interdisciplinary team is proposed to integrate planning and design activities and conduct them earlier in the process. This includes (new) collaborations with re-use experts. It is also found that the motivation of the team members could impact the amount of re-use. These findings are translated into a project management framework and in the visualization of the re-use process in a flow chart. These can be used by project managers in future re-use building projects.

This project develop a new method to generate breakline from the point cloud directly with the MAT. The breakline is a structured line of the object surface which has high curvature. Meanwhile, the reciprocal of the medial edge ball's radius can represent the point with high curvature, which is the fundamental idea of this project. The key parts of the method are: (a) with the help of MAT detecting candidate points having high curvature; (b) connect the candidate points to get breaklines with graph theory or polynomial fitting. The topology of the breakline is considered. In addition, this project also provides the polyline simplification and smoothing. In the resulting breakline, 27/32 are true positive. In general, the average correctness is 97% and 96%, the average quality is 90.67% and 91.19%, and the average completeness is 93.84% and 93.92% for valley and ridge. Most of accuracy parameters are above 80%. The accuracy is high. As to the precision, the average polyline precision is 0.3 and 0.23, and the average vertex precision is 1.14 meter and 1.12 meter. Comparing with the point density 2 pts/m^2. 25 of 27 breaklines' polyline precision is better than 0.5. 16 of 27 breakline's vertex precision is better than 1.0; and 23 of 26 is better than 1.5. The precision is also good. The source code is on Github: https://github.com/qq2012/geoflow-nodes.

The use of 3D models has been rapidly expanding, finding applications in both
scientific and commercial fields. One common requirement for these various applications is the geometrical and topological validity of these models. However, many models available online contain deficiencies in various forms, such as duplicated geometry, gaps in the surface, etc.. To cope with those deficiencies, a standard solution is the clean extraction of the model’s boundary, and simultaneously the model’s reconstruction in a way that its structure is valid. This thesis tackles a more generalized problem, the inside-outside classification for these models. Where many approaches might have requirements for running analysis, the methodology presented strives to robustly handle all cases.
These last decades, there have been various approaches in solving the ”inside -
outside classification problem”. A major attempt utilizes the winding number
algorithm, in order to assign values to elements whose position is relevant to the
input model. By assessing that value, a decision on whether the element in question is interior or exterior is taken. Other approaches work with casting rays, or other geometric analysis to also identify the borders of a model and segment the interior from the exterior. Also, since deficiencies inhibit the kick-starting of the necessary analysis, there are methods that try to restructure said models in order to clear any existing deficiencies. The methodology within this thesis will attempt a different approach from those that have been presented until now, which is transferring the problem from three into two dimensions. The first step is introducing a planar cross section on the area of interest. From there, through some graph reconstruction, geometric and optimization applications, a valid 1-manifold boundary of the cross-section is created. On that, the application of inside-outside classification through ray casting is possible. Assessing the results of the pipeline proves that the automated process can produce valid results, for a particular point of interest, related to an input model. The pipeline has been proven to function regardless of the cutting plane’s orientation, and can handle robustly a multitude of geometrically and topologically defective models. The results from this thesis can inspire further applications, and improvements on the pipeline can further evolve the quality of its outcome.

In recent years, there is an ever-increasing demand — both by industry and academia — for 3D spatial information and especially, for 3D building models. One of the ways to acquire such models derives from the combination of massive point clouds with reconstruction techniques, such as Ball Pivoting and Poisson Reconstruction. The result of these techniques is the representation of individual buildings or entire urban scenes in the form of surface meshes — data structures consisting of vertices, edges and faces. Despite their usefulness for visualization purposes, the high complexity of these meshes, along with various geometric and topological flaws, stands as an obstacle to their usage in further applications, such as simulations and urban planning. To address the issue of complexity, the production of lightweight building meshes can be achieved through mesh simplification, which reduces the amount of faces used in the original representations. Moreover, simplification methods focus on conforming the resulting mesh to the original one, in order to minimize the differences between the two of them. As a consequence, simple and accurate building models are possible to be acquired, whose geometric and topological validity is yet questionable. In this thesis, we introduce a novel approach for the simplification of building models, which results into a more compact representation, free of topological defects. The main characteristic of our method is structure awareness — namely, the recovery and preservation, for the input mesh, of both its primitives and the interrelationships between them (their configuration in 3D space). This awareness asserts that the resulting mesh closely follows the original and at the same time, dictates the geometric operations needed for its construction in the first place — thus providing accuracy, along with computational efficiency. Our proposed methodology is divided into three main stages: (a) primitive detection via mesh segmentation, (b) storage of primitive interrelationships in a structure graph and (c) simplification. In particular, simplification is accomplished here by approximating the primitive borders with a building scaffold, out of which a set of candidate faces is defined. The selection of faces from the candidate set to form the simplified mesh is achieved through the formulation of a linear binary programming problem, along with certain hard constraints to ensure that this mesh is both manifold and watertight. Experimentation reveals that our simplification method is able to produce simpler representations for both closed and open building meshes, which highly conform to the initial structure and are ready to be used for spatial analysis. Additionally, a fairly good approximation of a given mesh is possible to be obtained within reasonable execution times, regardless of the initial noise level or topological invalidity. Finally, a comparative analysis shows that the accuracy of our method stands in parallel with that of other available simplification techniques.

This thesis proposes a novel medial axis transform (MAT) based method to achieve visibility analysis in a point cloud. There are several advantages of this MAT based method. This method avoids surface reconstruction from a point cloud. It also works for the situation when there is surface missing in the input point cloud. For different point cloud datasets such as point cloud generated from meshes, AHN3 point cloud and point cloud generated from dense image matching, this method successfully deliver decent visibility result for all of them. The main challenge overcome in this thesis is the interior and exterior MAT separation. Two approaches, normal reorientation approach and bisector based approach are experimented in the thesis to separate MAT. The normal reorientation approach only works for point cloud generated from meshes. The bisector based approaches works for all the datasets testes. It successfully separates the interior and exterior MAT when there is surfacing missing. To speed up of the query process, spatial index is generated for interior MAT. In this thesis, two spatial indices are implemented, KD-Tree and R-Tree. Due to the limitation of my KD-Tree implementation, the KD-Tree does not improve the running speed obvious. There is a room to improve the KD-Tree implementation. The R-Tree achieves sharply improvement on running time of the queries. For 51567 points, the query based on R-Tree finished in 1880 ms. In a word, this thesis proposed an efficient MAT based method of visibility analysis in a point cloud.

There are several 3D city models available openly, worldwide. These models are used in various applications, from which many expects a homogeneous Level of Detail (LoD). Validating the accuracy of the LoD of a model requires the inference its LoD class and its conformance to the real-world object. This process quickly becomes infeasible for large models when done manually. Yet there is no automatic method for LoD inference and validation. Therefore the thesis proposes a method to automatically infer the geometric LoD (LoD0-2.3) in 3D city models.

A central aspect of this work is the use of machine-learning to classify building models based on their LoD. It follows the assumption that a process is possible where a classifier trained in a synthetic 3D city model containing all LoD classes, and applied in real city model. Therefore ten geometry measures (features) are computed from the objects and tested with six classification algorithms. The six experiments the transferability of a classifier from the synthetic city model to the real one, multi-class (LoD0-2.3) and binary (LoD2 or not) classification, and the effect of LoD class imbalance by introducing various amounts of LoD1 objects into the LoD2 model. Furthermore, by using a point cloud as ground truth, this explored the possibility of validating the inferred LoD classes.

The results indicate that the classifier is not transferable to the real data set when trained on the synthetic city model, which is probably due to the significant difference in object shapes between the two models. Binary classification outperforms the multi-class case and it is favourable for LoD validation where the main question is whether the model conforms the stated LoD or not. Finally, class-imbalance can reduce the classification with as much as 20%.