Modelling, prediction and control of the spread of aquaculture diseases with AI and network simulation

Modelling is an important tool to help understand the spread and impact of disease and provides a means through which to optimise surveillance and control measures. Social network analysis and associated modelling approaches are commonly applied tools. These approaches model the connections between individuals or locations by a variety of means and allow inferences to be made as to how rapidly a pathogen may spread through the contact network and allow individuals at high risk of getting or spreading a pathogen to be identified. A key limitation of such models is they assume the network is constant, behaving in the same way over time and in the event of a disease incursion or interventions. For example if a farmer is aware of the presence of a disease in the vicinity of their supplier, they may choose to seek another supplier, which may in turn influence that suppliers ability to supply their normal customers thus causing the network to rewire through a cascade of changes to the underlying structure. Though stochastic simulations and the addition of random connections can help reduce the consequences of this limitation, there remains a fundamental lack of understanding of behaviour response which could lead to false inferences relating to disease impacts and the effectiveness of responses.

Working with the Centre for Environment, Fisheries and Aquaculture Science (Cefas), an executive agency of the UK government’s Department for Environment, Food and Rural Affairs (defra) that is responsible for the control of diseases in aquaculture in England and Wales, this PhD studentship aims to develop a dynamic network simulation model (based on an existing framework) that includes behavioural responses to disease outbreaks and control measures. The project will deliver a network simulation tool that can be applied to investigate disease outbreaks and uses state-of-the-art methods and technologies from other more advanced fields to which network models are applied, such as communications and power networks. This tool will be developed in parallel to an R&D project run by Cefas and funded by defra to understand aquaculture site holder behaviours and trading patterns, which will be used to inform the network structure and it’s response to different key scenarios. Though focussed on aquaculture diseases, it is envisaged that the outputs from the proposed project will be applicable to a wide variety of other systems where understanding progression of an agent or process through a network is of interest.
This project will build on a social network modelling framework previously developed by Cefas through the inclusion of artificial intelligence approaches, machine learning algorithms, complex network analysis tools and latest epidemic spreading models to predict how a network may rewire and evolve in the event of a disease outbreak and subsequent control scenarios.

How to apply:

Applications are made via Bournemouth University’s website by clicking ’institution website’ button. If you have an enquiry about this project please contact us via the ’Email institution’ button, however your application will only be processed once you have submitted an application form as opposed to emailing your CV to us.

The BU PhD Studentships are open to UK, EU and International students.

Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 4 years and must demonstrate:
• outstanding academic potential as measured normally by either a 1st class honours degree (or equivalent Grade Point Average (GPA) or a Master’s degree with distinction or equivalent
• an IELTS (Academic) score of 6.5 minimum (with a minimum 6.0 in each component, or equivalent) for candidates for whom English is not their first language and this must be evidenced at point of application.