The widely reported death of two-year old Awaab Ishak in Manchester underscored the health risks of mould, a type of indoor air pollutant. This project will develop AI models to predict mould severity levels and produce a toolkit to raise the public’s awareness and practice effective measures to control mould.
Department: Geography & Environmental Science
Supervised by: Prof. Hong Yang
The main objectives of this project are to (1) develop AI models to predict mould severity levels at home; (2) develop a toolkit to raise the public’s awareness of mould and practice effective measures to reduce the risk. The widely reported death of two-year old Awaab Ishak in Manchester underscored the health risks of mould. As a kind of indoor air pollutant, mould can have multiple health effects, including asthma, respiratory infections, and mental health problems. The COVID-19 pandemic has caused more people to spend longer time at home and an increasing preference to work from home. Climate change can cause more floods, exacerbating the risk of mould. Despite the importance of reducing carbon emissions from homes, it is equally important to minimise the potential consequences around mould. This project will analyse England’s Home Energy Efficiency scheme data and DTU data. The student will also use the Wave Plus sensor to measure temperature and humidity used in later mould modelling. Based on traditional models, this project will develop machine learning Multiple linear regression (MLR), Random forest (RF), and Artificial neutral network (ANN) models to predict mould severity levels. Collaborating with Reading Council, this project will produce a booklet including possible hazardous mould and policies and practices to reduce mould (Survey, Mould treatment, Ventilation and Record keeping). This project will contribute to understanding the risks of module under climate change. This can pinpoint the policy interventions required to mitigate the mould risk and protect human health, particularly children.
The student’s tasks will include 1) analysing England’s Home Energy Efficiency scheme data and DTU data, including mould, temperature, relative humidity and exposure time; 2) using the Wave Plus sensor to measure temperature, humidity and air pressure at around ten houses/rooms on Whiteknights campus and in Reading; 3) developing machine learning MLR, RF and ANN models to predict mould severity levels; 4) developing a toolkit for identifying the risk of mould at home and practicing effective measures to prevent and remove mould; 5) writing a project report. There will also be opportunities to contribute to an academic publication, present at a conference, and work on the project’s communication and media plans.
Essential Skills: A basic understanding of mould or indoor air pollution. Able to organise own work and prioritise to ensure delivery on time and on specification. Willingness to learn new research techniques. Able to effectively read literature and synthesise findings. Good IT skills, including Microsoft Office. Good quantitative skills and programming experience in Python or R. Good oral and written communication skills. Desirable Skills: Experience in planning and carrying out small research projects. Project management skills.
The student will learn a mix of both technical and analytical skills that will be useful in both research and non-research careers. The student will learn to (1) read and analyse scientific literature related to the research area; (2) analyse mould and indoor air quality data; (3) measure air temperature and humidity using portable sensors; (4) run AI models using Python or R; (5) analyse data; and (6) interpret and present the data. If successful, this will hopefully lead to a publication or poster presentation.
The placement will be based in the School of Archaeology, Geography and Environmental Science. Some measurement will take place on multiple sites on Reading Whiteknights Campus and in Reading.
Full-time (35 hours per week), or the possibility to work part-time, to be discussed with the PI - start and end dates.
Monday 12 June 2023 - Friday 21 July 2023
The deadline to apply for this opportunity is Friday 21st April 2023. Students should submit their CV and Cover Letter directly to the Project Supervisor (click on supervisor name at the top of the page for email). Successful candidates will be invited for an interview.