Local Climate Zone (LCZ) classification plays a crucial role in understanding and managing urban environments, particularly through the lens of Land Surface Temperature (LST) behavior. This study investigates the effectiveness of a Convolutional Neural Network (CNN) with U-net architecture for classifying urban LCZs using spatio-temporal thermal imagery.

The research addresses several key sub-questions, including the creation of a representable training dataset, optimizing hyperparameters for the U-net model, and assessing the impact of temporal factors on classification performance. An unsupervised clustering approach was adopted to label the training data, utilizing the Iterative Self-Organizing Data Analysis Technique (ISODATA) algorithm on stacks of thermal images to generate clusters based on thermal behavior, which were then manually refined and validated. Through experimentation, optimal hyperparameters were identified: a learning rate of 0.001, a patch size of 64, and the SparseCategoricalCrossentropy loss function. The study also highlights the significant influence of temporal factors, when using daytime and Spring/Summer thermal images for training and testing the model better classification outcomes were obtained compared to nighttime and Autumn/Winter images.

The research contributes to the LCZ classification by incorporating both spatial and temporal dimensions of LST patterns, providing valuable insights for urban planning. The findings demonstrate that a CNN with U-net architecture is highly suitable for classifying urban LCZs, particularly when the dataset captures diverse seasonal and extreme conditions. This approach offers a robust and adaptable framework for urban environmental monitoring and planning. This thesis has explored the utilization of a new source for LCZ classification, providing a useful starting position for further enhancement of standardized LCZ classification. Future work is therefore recommended to focus on integrating additional geospatial data sources, refining classification categories, and integrating the standardized LCZ classification system by Stewart and Oke [2012].

The NMCAs (National Mapping and Cadastral Agencies) of European countries have different cadastral survey accuracy standards (European Global Navigation Satellite Systems Agency, 2019). In order to meet these standards, the appropriate equipment and services should be determined. The augmentation service Galileo High Accuracy Service (HAS), that is planned for 2022, will provide high accuracy Precise Point Positioning (PPP) corrections. Unlike other high-accuracy services, the Galileo HAS will be free of charge and available worldwide, without the need to be close to a base station or to a dedicated provider network. The PPP corrections will be provided through the Galileo signal as well as through the Internet (EUSPA, 2021). Because of the potential of the Galileo HAS, for the Synthesis Project we want to get insight in the accuracy of the augmentation service. Since a big share of cadastral surveys is performed in the built environment, we also want to determine the accuracy in an urban canyon. With the found accuracy, we can possibly judge whether Galileo HAS is suitable for cadastral surveys in the Netherlands, by comparing the measured accuracy to cadastral survey accuracy standards of the Dutch Kadaster.
As a final conclusion for this project, Galileo HAS is still a technique under development and the PPP-based correction methods are currently not as accurate as the RTK-based ones. Galileo HAS will present in the future ways to correct these errors.