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

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.