Case Studies

AS&RU has led - with the Alan Turing institute - to transfer Bayesian causal technologies so that these are suitable to monitor and help frustrate a foreign adversary trying to influence a democratic election either through a bot attack or electronic theft. Again AS&RU not only developed the methodology and code to help defend such attacks but also delivered tools enabling this defence.

AS&RU were one of the designers of the first Warwickshire Food Strategy which aims to tackle food insecurity under three headings: Affordability and access; Food education and choice; Sustainable choices. Research within AS&RU helped to shape the strategy and its delivery by contributing to the evidence base. AS&RU Director, Martine Barons, continues to be part of the Food Forum Partnership, enabling Warwick to be listed as a Key partner. Going forwards, AS&RU has been awarded grant funding to build statistical decision support to help reduce household food insecurity in Warwickshire.

ACORN is a Wellcome funded human health clinical antimicrobial resistance (AMR) surveillance project led by the Mahidol-Oxford Tropical Medicine Research UnitLink opens in a new window (MORU) and the Oxford University of Oxford Clinical Research UnitLink opens in a new window (OUCRU).

Existing AMR surveillance systems are based mostly on diagnostic microbiology laboratory antimicrobial susceptibility testing results alone, which limits interpretability of resistant proportions. Resulting data fail to give relevant feedback for treatment decisions for local clinicians and do not allow for direct assessment and subsequent modelling of the clinically relevant impacts and burden of drug-resistant infections (DRI). Tools to capture and analyse AMR data in low- and middle-income countries (LMIC) are scarce, which hinders engagement with and use of available data.

To fill these gaps, ACORN aims to develop and test a comprehensive data capture system for patient-focussed AMR surveillance and use the data to significantly reduce the burden and threat of AMR in LMIC settings. Dr. Busola Oronti is currently developing a decision support tool for antibiotics prescribing within the wider scope of the ACORN project using AI and machine learning methods. The tool will be used by healthcare professionals in LMICs and in a wider context to deliver optimal care to patients.

The project involves 19 participating sites across 10 countries in Asia and sub-Saharan Africa.

Within AS&RU and the Alan Turing Institute, a series of projects have helped various policing organisations in their efforts to frustrate criminal plots designed to perpetrate violence against the general public. We have now produced a statistical methodology and user-friendly supporting code for our clients to track and if necessary, intervene in such plots. Details describing the less sensitive parts of this work can be found in our paper doi:10.1214/19-BA1192

In a project with The National Archives, we built a decision support tool which allowed them to make a business case for investment in increased security of digital archives. Digital archives, and the materials held in them, are rich, complex and fragile. They are under threat from rapidly evolving technology, outdated policies and a skills gap across the archives sector internationally. However, since preserving digital objects is a relatively recent phenomenon in archival terms, a systematic study of the nature and relative importance of the risk structures had not been done. There was no consensus or consistency about relevant data collection, leading to data gaps. Building on a recently-developed Bayesian paradigm, the Integrating Decision Support System developed here at Warwick, we partnered with The National Archives, and other archives across the world to undertake a decision analysis and encode the results into a tool (DiAGRAM) to evaluate an archive’s risk profile and designed for easy use by archives nation- and world-wide.

DiAGRAM was a worldwide finalist in the Digital Preservation Coalition Awards 2020 and a worldwide winner of the Decision Analysis Practice Award 2022.

Pollinators are essential to human wellbeing - a large proportion of healthy food requires pollination, often by insects including bees. We set out to identify strategies that would ensure an adequate abundance of insect pollinators (honey bees, wild, bees, hoverflies, etc.) for food production. We were able to supplement data with rigorously collected quantities from experts using Structured Expert Judgment techniques to minimise the cognitive frailties that affect less structured approaches. The result is a model that can give probabilities to levels of insect abundance under a range of strategies and exogenous scenarios, including weather pattern shifts.

Working under CREDO have been eliciting from domain experts building Bayesian Nets of thousands of assets to populate a probabilistic digit twin of asset network failures. The proof of concept was first present was first presented at COP19 in Glasgow but currently this work is progressing to produce strategic decision support tools for guiding mitigations to ever more extreme flooding events driven by climate change. Our clients have been Anglian Water and we have a new beta Innovation project application to continue to roll this tool out for OfWat after a recent successful discovery phase. https://digitaltwinhub.co.uk/download/credo-technical-report-3-assessing-asset-failure/

The UK drive to net zero has led to a surge in the number of offshore wind power generators. These produce direct current power which then needs to be transformed into alternating current so that it can be efficiently and safely distributed onshore. As part of a project headed by Edinburgh University AS&RU are helping to produce Bayesian decision support to help decide how to configure the cathedral like DC circuit breakers which ensure the safe translation of DC to AC power.