Hyperspectral imaging, with its capability of capturing information beyond the visible spectrum, can offer detailed spectral signatures that are critical in various applications, ranging from environmental monitoring to medical diagnostics. However, a significant challenge arises when dealing with hyperspectral data due to the mixed-pixel phenomenon, where a single pixel contains spectral signatures from multiple materials. To solve this problem, hyperspectral unmixing (HU) is used to decompose mixed pixels into their constituent endmembers and their corresponding abundances. This study
introduces a novel approach that utilizes least squares optimization methods under various constraints for abundance estimation, specifically using quadratic programming (QP). Additionally, a Principal Component Analysis (PCA) based k-means clustering method is presented for endmember extraction. The research also explores the potential of using Weighted Total Least Squares (WTLS) to refine the estimation process iteratively for the abundance and endmember solutions. The results demonstrate that the type of constraints, whether Weighted Constraints (WC) or Hard Constraints (HC), significantly
influences the accuracy of abundance estimation. The QP model, when optimized with appropriate regularization and constraints, showed substantial improvements compared to standard unconstrained least squares methods. The newly proposed PCA method for endmember estimation outperforms traditional methods such as Vertex Component Analysis (VCA). Furthermore, while the WTLS method was sensitive to initial inputs, it showed potential for further enhancing the solutions derived from the QP and PCA methods.

The demand for commercial aviation is growing at an annual rate of 4%, posing significant environmental challenges. Large-capacity aircraft designed for long ranges are often used on short-to-medium range routes, leading to inefficient fuel consumption and higher emissions. With a future market need for aircraft seating 211 to 300 passengers, there is a clear gap for such a passenger airliner. This report examines the feasibility of the X-300 EcoFlyer, a proposed short-to-medium range aircraft with reduced environmental impact. Designed to carry 300 passengers over 3000 km, the X-300 aims to achieve 25% lower CO2 emissions, 50% lower NOx emissions, and 20% lower noise emissions compared to the Airbus A320neo. The study covers aircraft functions, system design, performance analysis, manufacturing, sustainability, operations, logistics, business viability, and technical risks. The findings confirm the X-300 EcoFlyer's potential to meet future demands with lower environmental impact. Innovations include a noise-shielding fuselage, a water-injected turbofan engine, in-wheel electrical taxing, and an electrical environmental control system. Overall, the X-300 EcoFlyer represents a promising solution to the challenges facing the future of high-capacity air transport.

In this multidisciplinary project several aspects of geosciences are combined. The regional geology background was summarized and linked to the borehole data.
Multiple tests were conducted on the well to answer several questions. The slug test indicated that the fracture is still open and essentially confirmed that it is a shear fracture, however it is unclear to what extent that the fracture is open. The fracture seems to be hydraulically connected to a permeable unit or shallow aquifer. Unfortunately, the length of the fracture could not be determined with the data collected from the test.
Electrical resistivity tomography (ERT) and seismics were both applied to a location near the borehole to acquire lateral information of the subsurface. The ERT results showed that the layers were horizontally continuous and indicated layers with different compositions based on resistive properties.
Seismic refraction tomography conducted along a part of the same profile showed similar results as the ERT for that part of the profile. P-wave velocities indicate a horizontally layered subsurface in the upper 40m. Additionally surface wave analysis of the same setup utilizing active and passive measurements resulted in a vertical s-wave velocity profile that can be used for future implementation of the planned Borehole Thermal Energy Storage (BTES) system.
The last geophysical method was using gravity data on the region around the site. A map was made by using available data on changes in gravity in the region and plotting the results. On this map the location of remnants of volcanos and the Litoměřice deep fault can be recognised.
Thermal properties of cores were analyzed using a Hot Disk and an optical scanner. Unfortunately the drilling of a new well from which the cores were to be analyzed was delayed, and cores from an uranium mine were used. This way the advantages and disadvantages of both measuring devices could be argued and used for future research.
Past analysis of geothermal regions have shown that exploration of geothermal energy causes surface displacement. It can also be observed during the drilling phase. Interferometric Synthetic Aperture Radar (InSAR) and Global Navigation Satellite System (GNSS) are valuable tools to monitor land surface changes. Measurement of surface deformation being one of its many applications. For this study, the above tools have been used to measure surface displacement in the region of Litoměřice.

Various tasks in the construction industry are tedious due to the high amount of repetition or time-consuming nature. In recent years Deep Learning within computer vision has made it possible to automate various tasks using images. The Hoofdvaarweg Lemmer-Delfzijl has been assessed using images and a pointcloud. The images were being worked with two employees over a month. This is time-consuming and there are a lot of images to go through.

Our project statement is thus: Develop a tool using computer vision techniques to reliably detect problematic corrosion on piling sheet within 4-5 months to understand what the state is of this topic for asset managers.

We first start with an analysis in which we looked at the existing the literature, the data, the existing methods and how Witteveen+Bos is assessing the images. We then set the requirements to which the algorithm should adhere to. Literature study has shown that most models, with data-sets of above 3000 images, achieve above 90% for both accuracy and mean average precision. Afterwards we start writing the algorithm and model testing various model structures as part of the synthesis procedure. The models are variating in structures, filters, depth, and augmentation.

We created a classifier, of four and six classes, and an object detection algorithm and conducted various evaluation techniques. The four-class classifier performed better than the six-class classifier. This could be due to the six-class classifier being made up of less data, classes that are vague, parts of the data showing imbalance problems.

An object detection algorithm was created to detect dimensional features to estimate the height above water and distance of the bumps. To convert the pixel distance to actual distance, we trained the model to detect a reference object. The object detector performed well, but did not meet the requirements we set. The dimension estimation provided can only provide a rough estimation. This may be the result of not every image, in the training set, contained a reference object. Creating the data-set was a tedious task and our data-set with two classes, took around eight hours to finish training.

We can conclude that for image classification, the structure of the model and the trainable parameters play a role. The object detector can count elements, but the predicted bounding box is sometimes larger than expected. Some recommendations are to increase data and classes. A robust feasibility for Witteveen+Bos regarding AI. Repurposing the algorithm for progress monitoring and exploring the interoperability between software relevant for the manager.

The Eastern Scheldt storm surge barrier (ES-SSB) is the largest hydraulic structure in the Netherlands. Its semi-open inlets allow for North Sea waters to enter and leave the Eastern Scheldt estuary with each tidal cycle, and can be closed during extreme storm events. The flow through the barrier is strongly contracted, and complex flow patterns emerge. Among characteristic flow features are the shallow jet and shallow mixing layer, generated as a result of large transverse shear stresses with horizontal lengths scales greatly exceeding the water depth. Large mean velocities in combination with the developing lateral non-uniformity of the flow between slack water and maximum flood gives rise to higher bed shear stresses. A bed protection up to a distance of about 600 m from the barrier is applied to stabilize the bed against increased hydraulic loading. Scour hole development adjacent to the applied bed protection was anticipated for, but expected equilibrium depths have not yet been reached. Reaching local depths of 60 m with respect to the water surface, these scour holes may on the long term be a threat to the stability of the barrier. Broekema (2020) concluded that during flow contraction, separation of flow near the bed of the scour hole is suppressed and high flow velocities in streamwise direction are found near the bed. Cyclic variations in lateral non-uniformity affect turbulence intensities and subsequent mixing of mass and momentum. Scour growth is therefore enhanced in two ways: i) velocities in the main flow remain high due to horizontal flow convergence, and ii) lateral velocity gradients are associated with larger turbulence intensities that are likely leading to larger bed shear stresses...

Bathymetric depth for shallow water regions is essential for coastal management and research. The measurements using echo sounding and LiDAR leave data gaps because vessels cannot reach nearshore waters or the green laser unable to penetrate specific areas. Satellite-Derived Bathymetry (SDB) is an alternative to extract shallow water depths that is able to overcome these problems using multispectral imagery. There are two approaches of SDB: analytical and empirical. The analytical method requires several water properties, which might not be known. The empirical method relies on the linear relationship between reflectances and depths, but the relationship may not be entirely linear due to bottom types variation, water column, and noise. Machine learning approaches have been used to address nonlinearity, but it treats pixels independently, whereas there is a spatial correlation that influences SDB computations since adjacent pixels are correlated to depth. This characteristic of the local connectivity can be captured by Convolution Neural Networks (CNN). Therefore, this thesis conducts a study of SDB using CNN.

This research focuses on the following questions: (i) what kind of preprocessing is needed for the data sets; (ii) what kind of CNN architecture can be used; (iii) what is the accuracy of the method; and (iv) to what extent the pretrained model in certain areas can be reused in other areas. In order to represent a variety of depth, bottom type, turbidity, and water column properties, this study chooses six areas of interest in three different coastal regions: Puerto Rico, Key West, and Hawaii.

With several CNN configurations, the optimum accuracy is obtained using three convolutional layers, a window size of 9x9, and the RGBNSS bands. Based on the experiment and comparison to the previous studies, the accuracy of SDB using the CNN approach outperforms the linear transform, the ratio transform, Random Forest, and the radiative transfer model. The results show that the accuracy decreases as the depth increases and in more turbid water. Comparison between different image preprocessing indicates another benefit of CNN: removing the need to preprocess images since suitable corrections can be automatically performed by CNN given adequate training.

The use of multi-temporal images enhances the variety of training data and thus improves SDB accuracy. However, data variation should be equally distributed to avoid abnormality in the result. Transfer model analysis indicates several limitations of SDB results at particular depths or when implemented to a different water condition, making the coastal water characteristics considered when reusing a pretrained model from one area to another.

In summary, CNN does not require additional image preprocessing and features specifications for training. CNN can produce better SDB accuracy than several other methods. The accuracy improves by increasing the variety of training data. However, SDB using the transfer model still need to be further investigated. A thorough identification of the proportion of sample data is needed to obtain balanced training data. In this way, it is more likely to produce a more reliable and more stable CNN model for extracting shallow water depths in the new data.

In recent years, unstable quay walls are a problem in The Netherlands. 100-year-old quay walls in cities like Amsterdam are collapsing and endanger people and property. The government needs to renovate unstable quay walls quickly. With 600 kilometre of quay wall in Amsterdam alone, this is a great challenge. Currently, unstable walls are found by deformation monitoring using tacheometry, which takes too much time for large scale monitoring. To increase both speed and coverage, a photogrammetric deformation analysis is proposed. In multiple epochs, at months interval, a series of images of the quay wall is made from a boat. In these images, feature points are identified and matched, where part of the feature points are matched across multiple epochs. All feature point observations are put in a multi-epoch least squares adjustment. This adjustment integrates both feature point observations of individual epochs and point deformations between multiple epochs. Using photogrammetry in combination with such a deformation adjustment has not been done previously, but has great advantages. The least squares adjustment allows to take the stochastic nature of the observations into account. This enables proper error propagation, such that not only quay wall stability can be assessed, but also the corresponding error budget. Results show that using two epochs 300 multi-epoch feature points can be found per square meter quay wall. With these points, sub-centimetre deformation can be estimated.