Risk EvaLuatIon fAst iNtelligent Tool (RELIANT) for COVID19
Lead Research Organisation:
University of Glasgow
Department Name: School of Engineering
Abstract
This project brings together unique expertise in Computational and Experimental Fluid Dynamics, Model Reduction and Artificial Intelligence, to identify solutions for the management of people and spaces in the current pandemic and post lockdown.
A new interactive tool is proposed that evaluates the risk of infection in the indoor environment from droplets and aerosols generated when breathing, talking, coughing and sneezing. This capability will become more critical as winter approaches and building ventilation will need to be limited for comfort considerations. The fluid dynamic behaviour of droplets and aerosols, the effect of using face masks as well as other parameters such as room volume, ventilation and number of occupants are considered. A datahub capable of storing, curating and managing heterogeneous data from sources internal and external to the project will be created. A synergetic experimental and numerical approach will be undertaken. These will complement the existing literature and data from other EPSRC-funded projects providing suitable datasets with adequate resolution in time and space for all the relevant features. To support experiments and numerical simulations, reduced order models capable of interpolating and extrapolating the scenarios collected in the database will be used. This will permit the estimation of droplet and aerosol concentrations and distributions in unknown scenarios at low-computational cost, in near real-time. A state-of-the-art AI-based framework, incorporating descriptive, predictive and prescriptive techniques will extract the knowledge from the data and drive the decision-making process and provide in near real-time the assessment of risk levels.
A new interactive tool is proposed that evaluates the risk of infection in the indoor environment from droplets and aerosols generated when breathing, talking, coughing and sneezing. This capability will become more critical as winter approaches and building ventilation will need to be limited for comfort considerations. The fluid dynamic behaviour of droplets and aerosols, the effect of using face masks as well as other parameters such as room volume, ventilation and number of occupants are considered. A datahub capable of storing, curating and managing heterogeneous data from sources internal and external to the project will be created. A synergetic experimental and numerical approach will be undertaken. These will complement the existing literature and data from other EPSRC-funded projects providing suitable datasets with adequate resolution in time and space for all the relevant features. To support experiments and numerical simulations, reduced order models capable of interpolating and extrapolating the scenarios collected in the database will be used. This will permit the estimation of droplet and aerosol concentrations and distributions in unknown scenarios at low-computational cost, in near real-time. A state-of-the-art AI-based framework, incorporating descriptive, predictive and prescriptive techniques will extract the knowledge from the data and drive the decision-making process and provide in near real-time the assessment of risk levels.
Publications
Cheng M
(2022)
Spatio-Temporal Hourly and Daily Ozone Forecasting in China Using a Hybrid Machine Learning Model: Autoencoder and Generative Adversarial Networks
in Journal of Advances in Modeling Earth Systems
Esfandiary M
(2023)
On the effects of surface waviness upon catalytic steam reforming of methane in micro-structured reactors - a computational study
in International Journal of Hydrogen Energy
Guo Y
(2021)
Variational Gaussian process for optimal sensor placement english
in Applications of Mathematics
Heaney C
(2022)
An AI-based non-intrusive reduced-order model for extended domains applied to multiphase flow in pipes
in Physics of Fluids
Martinelli C
(2023)
Approximating piecewise nonlinearities in dynamic systems with sigmoid functions: advantages and limitations
in Nonlinear Dynamics
Mesgarpour M
(2023)
A combination of large eddy simulation and physics-informed machine learning to predict pore-scale flow behaviours in fibrous porous media: A case study of transient flow passing through a surgical mask
in Engineering Analysis with Boundary Elements
Mesgarpour M
(2022)
Predicting the effects of environmental parameters on the spatio-temporal distribution of the droplets carrying coronavirus in public transport - A machine learning approach.
in Chemical engineering journal (Lausanne, Switzerland : 1996)
Mesgarpour M
(2021)
Prediction of the spread of Corona-virus carrying droplets in a bus - A computational based artificial intelligence approach.
in Journal of hazardous materials
Mousavi S
(2023)
On the effects of adding syngas to an ammonia-MILD combustion regime-A computational study of the reaction zone structure
in International Journal of Hydrogen Energy
Nikiteas I
(2021)
LOAD BALANCING ANGULAR ADAPTIVITY ON ENERGY DEPENDENT REACTOR PROBLEMS
in EPJ Web of Conferences
Phillips T
(2021)
Reduced-Order Modelling with Domain Decomposition Applied to Multi-Group Neutron Transport
in Energies
Phillips T
(2021)
An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion
in International Journal for Numerical Methods in Engineering
Phillips T
(2022)
Multi-Output Regression with Generative Adversarial Networks (MOR-GANs)
in Applied Sciences
Phillips T
(2023)
Solving the discretised neutron diffusion equations using neural networks
in International Journal for Numerical Methods in Engineering
Rahmani E
(2022)
A comparative analysis of the evolution of compositional and entropy waves in turbulent channel flows
in Physics of Fluids
Rashidi S
(2022)
Progress and challenges on the thermal management of electrochemical energy conversion and storage technologies: Fuel cells, electrolysers, and supercapacitors
in Progress in Energy and Combustion Science
Saeed A
(2022)
Computational assessment of the thermal response of a Li-ion battery module to transient loads
in Journal of Power Sources
Salinas P
(2021)
Dynamic mesh optimisation for geothermal reservoir modelling
in Geothermics
Silva V
(2022)
Data Assimilation Predictive GAN (DA-PredGAN) Applied to a Spatio-Temporal Compartmental Model in Epidemiology
in Journal of Scientific Computing
Titus Z
(2021)
Conditioning surface-based geological models to well data using artificial neural networks
in Computational Geosciences
Wu P
(2022)
Navier-stokes Generative Adversarial Network: a physics-informed deep learning model for fluid flow generation
in Neural Computing and Applications
Wu P
(2021)
Reduced order model using convolutional auto-encoder with self-attention
in Physics of Fluids
Wu X
(2023)
Modeling for understanding of coronavirus disease-2019 (COVID-19) spread and design of an isolation room in a hospital
in Physics of Fluids
Zheng J
(2021)
Numerical study of COVID-19 spatial-temporal spreading in London.
in Physics of fluids (Woodbury, N.Y. : 1994)
| Description | The project has produced a few key findings and results that can be summarised as follow: 1- Means to characterise experimentally how exhaled gases propagate in the environment: the upper-air-way simulator at the University of Glasgow together with the salt bath technique at Cambridge University form a unique tool to reproduce and monitor in a repeatable way how exhaled gases propagate indoor. The setup has been used to study the efficacy of masks and shields and highlighted the danger of using face shields as a preventive measure to stop the spread of the virus. In fact, face shields direct the exhalation gases downward, potentially projecting the virus to people and surfaces positioned below the person wearing the shield. Masks are much more effective: they tend to contain the spread of the exhalations favouring the entrainment in the heating plumes and their stratification in the upper part of the environment. This results were communicated to HSE, NHS and advertised through social media. 2- High fidelity simulations of exhaled gas propagation in indoor environment: by using CFD models validated against experimental data, we characterised the mechanisms that influence the propagation of exhalation gases in the environment. The models permitted to assess the influence of the activities performed by the occupants (low or high breathing rate), the temperature and the presence of heaters and the effect of ventilation. A key finding is that the position of the ventilation and the type of ventilation (active vs passive) has a profound influence on the concentration of exhaled gases in the environment. The models also highlighted that higher ventilation rate are not always necessary and that there are other possible approaches to ventilation. This finding has profound implications on the energy management of building, especially during the cold season and has prompted an invitation of the research team at one of the exhibition for COP26 3- Artificial intelligence technology has been applied to the data collected experimentally and produced via CFD models and has facilitated the extrapolation to a number of scenarios that could not have been achieved otherwise. Through the use of risk quantification techniques such as Wells Riley, the concentration of exhaled gases has been converted in risk of infection. This tool requires further refinement. |
| Exploitation Route | There have been great interest in the work done so far. The investigatory team in currently in contact with the NHS to apply some of the skills developed in this project to hospital environment and help with the management of COVID patients. Also, the findings of this project could be fundamental to operate more wisely the heating and ventilation systems in building, paving the way to a more sustainable ventilation management in line with the new energy requirements. |
| Sectors | Communities and Social Services/Policy,Environment,Healthcare |
| Description | During this project we have been in contact with policy makers and with the NHS to inform them of our finding and support the development of policies that are affective against COVID19. In 2021, during a presentation to HSE, the investigatory team showed that shields do not offer an adequate level of protection and that can direct infected droplets and exhaled gases towards any object and person who is below the mouth of the person wearing the shield. We also demonstrated that masks are much more effective in reducing the risk of infection. |
| First Year Of Impact | 2021 |
| Sector | Healthcare |
| Impact Types | Societal,Economic,Policy & public services |
| Title | Upper Airway Simulator |
| Description | This is a test rig developed at the university of Glasgow to simulate in a reproduceable manner the gas exhalation of a breathing person. The simulator is capable of replicate the breathing patterns of individuals with different lung capacities, ages and activities. The rig features heating mechanisms to replicate the temperature of a human being. |
| Type Of Material | Improvements to research infrastructure |
| Year Produced | 2022 |
| Provided To Others? | Yes |
| Impact | This tools is fundamental to study the propagation of exhaled gases and droplets in the environment and will be conducive to the advancement of technology in the following fields: 1- medical practice: our tools can help quantify the risk of infection from airborne disease during aerosol generating procedures. Impact not yet realised 2- Built environment: through this rig experimental models it was possible to assess the efficacy of ventilation in indoor environment. This has been conducive to activities with Estate and Buildings office at the university of Glasgow to reduce the risk of infection in classes and meeting rooms |
| Description | COP26 outreach activity |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | This activity was part of COP26: the project Reliant was identified for it potential to help address the conflictual need of high level of ventilation in indoor environments and minimisation of energy usage and CO2 emissions. The activity took place in Glasgow in November 2021 and provided a great engagement platform to disseminate the findings of the project and provide some solutions to address this problem. During this event the research group made contact with a few stakeholders, including policy makers, industrial partners and health and safety experts. This activity led to further activities for the application of the skills and tools developed in RELIANT to built environments. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Centre for Sustainable Solutions |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Professional Practitioners |
| Results and Impact | Presentation on the impact of ventilation on removing exhaled gases from indoor environment with analysis of the dissipation of heat that it creates. The investigatory team gave a presentation followed by a Q&A session. This led to a further activity where the research team engaged with "Estates & Building" at UoG to make the campus safer and more sustainable. |
| Year(s) Of Engagement Activity | 2021 |
| Description | ITV news at 10 |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | Interview at ITV on how engineering can support the fight against COVID19 |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://www.itv.com/news/2021-05-28/covid-how-can-indoor-spaces-be-made-safer-after-restrictions-are... |
| Description | Nuclear Institute Evening talk: Can Nuclear Modelling Techniques Help National Efforts to Combat COVID-19? |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Over many decades nuclear scientists and engineers have developed advanced techniques for modelling the behaviour of nuclear reactors under normal operation and accident conditions. These techniques have also been extended to other nuclear facilities and systems such as; decommissioning, nuclear and waste processing. Much of the phenomenology is analogous to the spread of a virus during a pandemic. For instance, the neutron multiplication factor in a nuclear reactor, k-effective, is in many ways analogous to the Reproduction Number (RO) in a pandemic. The transport of fission products on aerosols resulting from a nuclear reactor severe accident has many similarities with the spread of a virus on airborne aerosols. The presenters will explore such similarities and how the advanced modelling techniques developed in the nuclear industry can contribute to the simulation of the spread of a virus during a pandemic." |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://www.nuclearinst.com/Events-List/Could-Nuclear-Modelling-Techniques-Help-the-National-Efforts... |
| Description | Science on the Sofa: Structures, Airplanes and COVID19 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | Launched in 2007, Glasgow Science Festival (GSF) has grown to be one of the largest science festivals in the UK. GSF takes memorable events to non-traditional venues across the city where we engage with up to 60,000 people, from all ages and backgrounds, through the June festival and tens of thousands more through our community projects. The principal aim is to showcase the outstanding contribution Glasgow and Glasgow based researchers make to the worlds of science, technology, engineering, art, maths and social science (STEAM). We do this by developing content with researchers and by working with partners to produce a varied programme of activity featuring high quality events and innovative delivery styles. GSF combines a light hearted tone with seriousness of purpose, exploring STEAM and the social and ethical issues surrounding these subjects. |
| Year(s) Of Engagement Activity | 2020 |
| URL | http://www.glasgowsciencefestival.org.uk |