machine learning aided high-fidelity urban building modelling approach for energy-efficient, low-carbon and climate-responsive buildings

Project ID: 2228cd1247 (You will need this ID for your application)

Research Theme: Energy and Decarbonisation

UCL Lead department: Bartlett School of Environment, Energy and Resources

Project Summary:

Climate change increases the urgency to decarbonise buildings and make them more resilient. Urban-building modelling tools can help understand the impact of energy-efficient and climate-responsive building technologies across a large part of building stock; however, such tools are incapable of modelling the realistic and local microclimate of urban buildings, using simplistic static and pre-generated weather files. This may cause modelling errors that adversely influence the decision-making process. The UN SDGs emphasise the need for sustainable cities to be resilient under extreme weather, and this poses a modelling challenge to identifying buildings vulnerable to overheating under heatwaves and developing effective mitigation strategies. This project aims to develop a novel urban-building modelling approach to precisely model microclimate’s effects on urban buildings. The open-source data (e.g., LiDAR, satellite images) will be used to model the 3D morphology of urban buildings by deep learning techniques. The weather variables of the urban-building model at each timestep will be determined by an urban canopy microclimate model, which is formulated based on the identified urban-building morphology. A hybrid physics-machine learning modelling approach developed previously by the supervisory team will be used to establish the urban-building model and compute the dynamic response of individual buildings. The student will have access to the data of UCL East campus, where the supervisory team is working on to develop a digital twin platform (as part of a research project), to demonstrate the performance of the proposed modelling approach and analyse its ability to support practical scenarios under the current circumstance and future climate change for reducing energy consumption and mitigating overheating risks of buildings.
This project will benefit policymakers, local authorities, urban planners and building owners. The student will develop understanding on sustainable, low-carbon and resilient buildings and acquire skills in energy system modelling and machine learning techniques.