Development of Large Language Models for Guiding Net Zero Building Design

Project lead: Professor Franco Cheung

Project reference: CEBE-FC-ANODE

This research project aims to guide the design of environmentally friendly, energy-efficient buildings, otherwise known as Net Zero Energy Buildings (NZEB). The design process for these buildings is complex and time-consuming, as it involves understanding various aspects like energy use, environmental impact, and long-term costs.

Our goal is to create an artificial intelligence (AI) program that can make this process easier. This AI will be trained to understand building designs and provide all the necessary information for NZEB design.

The first step is to develop a common language that can be understood by both the AI and the building designs. Once that is established, we'll train the AI using these corpora and a variety of building designs along with their NZEB assessment data.

With this AI assistant, we hope to streamline the NZEB design process. This means architects and engineers can quickly access all the necessary information they need for their designs. The ultimate goal is to make the design process of environmentally friendly buildings more efficient and less time-consuming, thereby contributing to a more sustainable future.
 

Anticipated Findings and Contribution to Knowledge

This research extends the integration of AI in the building design field, particularly within advanced design and management tools like BIM and digital twins. It aims to deliver a transformative approach to Net Zero Emissions Buildings (NZEB) design, introducing an AI model that understands building designs and provides vital NZEB assessment information. This innovation is expected to streamline the assessment process, offering instant access to accurate data, increasing assessment reliability, and reducing manual workload.

Beyond immediate applications, this research significantly contributes to two prominent areas: The integration of generative design technology in Building Information Modelling (BIM) and the advancement of digital twins as decision-making tools.

In the context of BIM, the AI model will enhance the generative design process. Generative design uses algorithms to create optimized design options, relying heavily on accurate data. Our AI model is designed to efficiently populate BIM models with necessary data, fostering a more efficient workflow, and enhancing generative design's contribution to NZEB goals.

For digital twins, virtual replicas of physical structures, the proposed AI model becomes instrumental. These digital counterparts require precise, real-time data. The model specifically focuses on simplifying the interpretation of building design language and generating essential NZEB assessment data. This contribution ensures that digital twins accurately capture the sustainability features of physical buildings, thereby enhancing their functionality as a robust decision-making tools.

Person Specification

We invite high-calibre graduates with a first-class BSc (Hons) or MSc in Computer Science, Building Information Modelling and Digital Construction or related fields to apply for this prestigious PhD studentship.

Ideal candidates will possess a robust understanding of Natural Language Processing and Large Language Models.

In your application, please articulate your relevant experience in Artificial Intelligence and Machine Learning, highlighting how your background aligns with the requirements of this position. This opportunity is tailored for individuals eager to advance in cutting-edge research domains.

International applicants must also provide a valid English language qualification, such as International English Language Test System (IELTS) or equivalent with an overall score of 6.5 with no band below 6.0. 

To discuss this project, please contact Professor Franco Cheung at franco.cheung@bcu.ac.uk

PhD Classic Doctoral Training Grant Funding Information 

This funding model includes a 36 month fully funded PhD Studentship, in-line with the Research Council values, which comprises a tax-free stipend paid monthly (2024/5 - £19,237) per year and a Full Time Fee Scholarship for up to 3 years, subject to you making satisfactory progression within your PhD.

All applicants will receive the same stipend irrespective of fee status.

Application Closing Date:
23:59 on Tuesday 1st October 2024 for a start date of the 3rd February 2025.

How to Apply 

To apply, please complete the project proposal form,ensuring that you quote the project reference (CEBE-FC-ANODE), and then complete the online application where you will be required to upload your proposal in place of a personal statement as a pdf document. 

You will also be required to upload two references, at least one being an academic reference, and your qualification(s) of entry - Bachelor/Masters certificate(s) and transcript(s).