Building heights are important information for a variety of subjects, such as wind analysis, energy demand simulations and solar potential assessment, yet large-scale LiDAR scanning is costly. This thesis introduces PHYSHADE: a set of physics-guided U-Net-based models. It employs shadow projections derived from building footprints and solar geometry into an aerial image shadow segmentation pipeline, for the purposes of building shadow extraction and consequently the large-scale estimation of building heights. Thirty-five aerial images in the Netherlands were manually annotated for buildings and their associated buildings. By employing transfer learning, based on a general purpose shadow-segmentation model, a total of 130 models were trained, which can be categorized into three different implementations of PHYSHADE. Through these different configurations, the performance impact of the various methods of addition of pseudo-shadows to the models was ablated. Afterwards, the best-performing PHYSHADE configurations were used with a raycasting algorithm to convert shadow lengths and solar altitudes back into building heights. The inclusion of pseudo-shadows lifted the mean Dice scores from 0.53 to 0.85, with an average gain of 0.32 and statistical significance across different folds. Physics-guided loss, based on the pseudo-shadows, was not found to be significantly different in most cases, whilst hurting model performance in some cases compared to the pseudo-shadow enabled models. On six out-of-fold test tiles the best PHYSHADE variants retained Dice scores of 0.72 – 0.95, although recall declined in one winter scene. Finally, height estimation on these tiles using the inference from the best PHYSHADE variants resulted in mean RMSE of ≅ 1.9m and MAE of ≅ 1.5m. While its application needs to be tested in broader contexts, PHYSHADE offers a viable low-cost complement to LiDAR for building height estimation.

This report details the development process of an open-data-based tool, an extension of the original interface created by Royal HaskoningDHV. The objective was to bridge the gap between geographical data and Architectural, Engineering, and Construction (AEC) industry applications. The tool aimed to transform spatial data for architects, facilitating contextual analysis in Rhinoceros and Grasshopper, ultimately aiding architects and engineers in enhancing designs based on environmental impact.

The initial tool focused on Netherlands data, but the ultimate goal was to make it applicable to other countries/regions. The research involved evaluating data availability for different regions, acquiring and aligning relevant data for Grasshopper, and implementing these data workflows into wind and solar analyses.

The data evaluation stage revealed challenges due to varying data availability and accessibility across countries. For example, Germany's fragmented data required navigating different portals, while Hong Kong's centralized data via API was more accessible. The lack of standardization hindered automation, necessitating manual data retrieval strategies that could be challenging for non-geomatics experts.

Data alignment methods varied, introducing complexities. For instance, Italy required 3D extrusion from 2D shapefiles, leading to unavoidable errors. Spain used a different method, showcasing the difficulty of a universal solution due to data standardization and interoperability issues.

Two techniques were envisioned for the open-data tool: TIN-based and Voxel-based methods, each with distinct qualities and limitations. The TIN-method offered high-quality analyses but required rigorous data alignment, while the Voxel-based method allowed flexibility but risked issues with resolution.

Limitations of exploratory analysis included a focus on five countries/regions and inherent constraints of Rhinoceros, limiting tool accessibility and requiring alternative approaches. Additionally, language barriers and data platform permeability might have led to overlooked datasets.

In conclusion, the report acknowledges the need for future work. Optimization of code for readability and performance is suggested, and the inclusion of additional data types (vegetation, land use, transport) in data workflows is proposed. Input from AEC professionals through methods like questionnaires or testing is recommended for further improvement. This report emphasizes the evolving nature of the tool and the importance of ongoing refinement to meet the needs of diverse AEC professionals.