###A high-fidelity coupled urban-building and microclimate modelling approach for energy-efficient and climate-responsive buildings
Project ID: 2228bd1208 (You will need this ID for your application)
Research Theme: Energy and Decarbonisation
UCL Lead department: Bartlett School of Environment, Energy and Resources
Lead Supervisor: Dimitrios Rovas
Project Summary:
Climate change instils urgency in the need to decarbonise buildings and empower them to be more resilient towards extreme weather to protect human health and comfort. 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 often rely on static, pre-generated typical-year weather files and do not consider realistic weather conditions and the local microclimate. This can lead to modelling discrepancies to the ground truth and misguide the subsequent decision-making process. This problem is more intense in megacity centres where a highly dense building morphology and complicated outdoor environment could significantly influence model prediction quality.
This project aims to develop a novel modelling approach, coupling urban building energy models with microclimate models. The weather variables of an urban-building model at each timestep will be determined by an urban canopy microclimate model formulated based on the identified urban-building morphology. The 3D morphology will be modelled using open-source LiDAR data, incorporating satellite images analysed by deep learning techniques. 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. We will use a university campus in central London as a case study 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 to make informed decisions facing climate change and urbanisation. The student will deepen their understanding of developing sustainable, low-carbon and resilient buildings and grasp skills in modelling energy systems and leveraging machine learning techniques.