This study investigates the application of machine learning (ML) for predicting building energy performance at city scale, with a focus on reducing heating and cooling demands under current and future climate scenarios. A two-part methodology was adopted, involving: (i) large-scale building energy simulation and (ii) ML model development. Using Rotterdam, Netherlands as a case study, a computational workflow was created to automate data collection, processing, and energy simulation for 20,000 residential buildings under both the present and two projected climate conditions. Results highlight the influence of building layout, envelope thermal properties, and air tightness on reducing energy demand across a diverse range of building archetypes. An artificial neural network (ANN) was subsequently developed to enable rapid prediction of energy demands for both existing building conditions and retrofit scenarios. The analysis demonstrates that a shallow ANN is an effective ML model in terms of time efficiency, usability, and accuracy, particularly for predicting heating demands. The study highlights both the strengths and limitations of ML-based approaches relative to traditional energy modelling, offering valuable insights for energy planning and targeted retrofit decision-making at city-scale.

The scripts created for the main computational workflow of this project are shared to the following github repository: https://github.com/elenarduzzi/buildingenergymetamodels

Urban climate affects how people move through cities, but its influence is difficult to capture with models based on generalized comfort indices that ignore individual experiences of climate. This thesis instead explores a bottom-up approach that uses daily Global Navigation Satellite System (GNSS) traces of people traversing an urban environment, which inherently contain each individual's personal influences on their mobility. A machine learning model was developed and trained using this dataset with the purpose of predicting future mobility values, while assessing the role that climate played in such predictions. The model employed a Spatio-Temporal Graph Neural Network (STGNN) architecture to capture both potential spatial dependencies between visited locations and temporal patterns in their activity.

The work draws on the Seoul Cozie dataset, which recorded six weeks of GNSS location data from wearable devices of 22 participants in Seoul during autumn 2023. Positions were aggregated into a graph structure with road intersections as nodes and transitions between them as edges. Climate features (temperature, humidity and PM10) were interpolated from over 1,000 weather stations using a Triangulated Irregular Network method and added as dynamic node features. STGNN variants were trained and compared based on whether they included climate node features.

Results show forecasts of node visits with low Mean Square Error of around 0.12 . However, precision and recall values for visited/unvisited node detection are low, peaking at 56.51%, reflecting strong class imbalance in the input. Adding climate attributes produced only minor and inconclusive improvements, in part due to the dataset’s short time span. The thesis proposes a reproducible framework linking climate and mobility, while underlining the need for richer datasets and for more flexible model architectures, capable of addressing class imbalances and representing personal mobility datasets.

This study investigates the relationships between urban form elements (UFEs), Urban Heat Island (UHI) effects, and building energy consumption in Heukseok-dong, Seoul, South Korea. Using 10 years of satellite imagery, air temperature measurements, and energy consumption data, the research examines how six UFEs (NDVI, building ratio, building height, building volume, FSI, and GSI) influence air temperatures and building energy consumption across multiple spatial scales and seasons. A Multi-Layer Perceptron (MLP) neural network was developed to convert satellite-derived Land Surface Temperature (LST) to air temperature, achieving an R2 of 0.9684, and tested with independent S-DoT sensors. The independent testing was conducted in two phases: for May-August 2020, the mean temperature difference was 1.84°C, remarkably close to the known systematic temperature difference of 1.8°C between S-DoT sensors and AWS. When extended to 2020-2024, the mean
difference was 0.98°C with an R2 of 0.807, confirming the model successfully predicts actual air temperatures rather than sensor-specific values. The Genizi method and partial correlation analysis were combined to address multicollinearity while revealing both relative importance and directional effects of UFEs. This complementary approach provides more comprehensive insights than traditional regression methods alone. Key findings reveal that NDVI dominates temperature variance in spring (79.3%), fall (64.7%), and winter (71.6%), but building characteristics become more important in summer, with building ratio contributing 71.8% at pixel scale. Scale-dependent patterns emerged, with energy consumption best captured at 100m scale (R2 up to 0.378) while temperature variations appeared more clearly at 300m scale (R2 up to 0.328). The cascade relationship from UFE through air temperature to energy consumption showed air temperature driving 54.3% of electricity variance in summer, while building volume consistently influenced both electricity and gas consumption despite EUI normalization. A decade-long analysis of District 3’s transformation from 478 low-rise buildings to 28 high-rise apartments confirmed the statistical findings. Despite a 2,112.6% increase in building volume and 168% improvement in NDVI, temperature trends showed 0.10-0.16°C/year increases, which are approximately half of Heukseok-dong’s 0.17-0.32°C/year rates, demonstrating that urban design can partially mitigate but not eliminate warming effects. The moderate R2 values (0.067-0.378) indicate that urban form elements explain only a portion of variance, partly reflecting the temporal limitation of correlating single hourly satellite observations with monthly energy totals. The research provides evidence-based recommendations for urban planning policies, including maintaining GSI below 0.55, achieving NDVI above 0.15, and implementing seasonal strategies for temperature mitigation and energy management.

Lowering energy demand in buildings is high on the political agenda considering household energy consumption accounts for 22% of the total final energy usage in the Netherlands. Tools that can run these types of simulations for an entire city are required for effective policy design to lower energy consumption within the built environment. This thesis explores how to build such a tool that allows for space heating demand to be computed that follows the NTA 8800 norm. Therefore, the main research question is: “To what extent can a heat demand model be developed that adapts and implements the NTA 8800 to be coupled with CityGML-based semantic 3D city models?”. The thesis uses a mixed-method research approach of qualitative concept mapping and quantitative modelling to build a space heating demand model for urban analysis. The final product is a Python-based model with database interactions, compatible with CityGML-based semantic 3D city models, following the NTA 8800 computation methods.

Initial testing on two buildings highlighted areas for model development, including the underestimating of ventilation losses and the omission of windows and doors in transmission estimates. Improved window quality could result in significant energy savings, according to the solar gain analysis. The model’s capacity to mimic anticipated trends in space heating demand was verified using benchmark data, although it deviated from previous consumption patterns, indicating the need for additional research. The model was tested for Rijssen-Holten and produced rapid results within 5 minutes. Despite limitations due to data availability and model assumptions, the thesis model underscores the utility of Geomatics in urban energy management and the results can help design energy policy design for sustainable development.