Final Report

Building design processes are dynamic and complex. The context of a building pro- ject is manifold and depends on the cultural context, climatic conditions and personal design preferences. Many stakeholders may be involved in deciding between a large space of possible designs defined by a set of influential design parameters. Building performance simulation is the state-of-the-art way to provide estimates of the energy and environmental performance of various design alternatives. However, setting up a simulation model can be labour intensive and evaluating it can be com- putationally costly. As a consequence, building simulations often occur towards the end of the design process instead of being an active component in design processes. This observation and the growing availability of machine learning algorithms as an aid to exploring analytical problems has lead to the development of surrogate mo- dels. The idea of surrogate models is to learn from a high-fidelity counterpart, here a building simulation model, by emulating the simulation outputs given the simula- tion inputs. The key advantage is their computational efficiency. They can produce performance estimates for hundreds of thousands of building designs within seconds. This has great potential to innovate the field. Instead of only being able to assess a few specific designs, entire regions of the design space can be explored, or instan- taneous feedback on the sustainability of building can be given to architects during design sessions. This PhD thesis aims to advance the young field of building energy simulation surrogate models. It contributes by: (a) deriving Bayesian surrogate models that are aware of their uncertainties and can warn of large approximation errors; (b) deriving surrogate models that can process large weather data (≈150’000 inputs) and estimate the associated impact on building performance; (c) calibrating a simulation model via fast iterations of surrogate models, and (d) benchmarking the use of surrogate-based calibration against other approaches. / Graduate

Building design can have a major impact on sustainability through material efficiency and construction waste minimisation (CWM). The construction industry consumes over 420 million tonnes of material resources every year and generates 120 million tonnes of waste containing approximately 13 million tonnes of unused materials. The current and on-going field of CWM research is focused on separate project stages with an overwhelming endeavour to manage on-site waste. Although design stages are vital to achieve progress towards CWM, currently, there are insufficient tools for CWM. In recent years, Building Information Modelling (BIM) has been adopted to improve sustainable building design, such as energy efficiency and carbon reduction. Very little has been achieved in this field of research to evaluate the use of BIM to aid CWM during design. However, recent literature emphasises a need to carry out further research in this context. This research aims to investigate the use of BIM as a platform to help with CWM during design stages by developing and validating a BIM-aided CWM (BaW) Framework. A mixed research method, known as triangulation, was adopted as the research design method. Research data was collected through a set of data collection methods, i.e. selfadministered postal questionnaire (N=100 distributed, n=50 completed), and semistructured follow-up interviews (n=11) with architects from the top 100 UK architectural companies. Descriptive statistics and constant comparative methods were used for data analysis. The BaW Framework was developed based on the findings of literature review, questionnaire survey and interviews. The BaW Framework validation process included a validation questionnaire (N=6) and validation interviews (N=6) with architects. Key research findings revealed that: BIM has the potential to aid CWM during design; Concept and Design Development stages have major potential in helping waste reduction through BIM; BIM-enhanced practices (i.e. clash detection, detailing, visualisation and simulation, and improved communication and collaboration) have impacts on waste reduction; BIM has the most potential to address waste causes (e.g. ineffective coordination and communication, and design changes); and the BaW Framework has the potential to enable improvements towards waste minimisation throughout all design stages. Participating architects recommended that the adoption of the BaW Framework could enrich both CWM and BIM practices, and most importantly, would enhance waste reduction performance in design. The content should be suitable for project stakeholders, architects in particular, when dealing with construction waste and BIM during design.