Skip to main content

The Alan Turing Institute

New research launched

During the course of 2019/20 the 24 University of Leeds Turing Fellows embarked on a series of new Turing research projects and activities. Led by LIDA Director and Turing Fellow Professor Mark Birkin the Turing’s new research programme in Urban Analytics expanded rapidly. The Urban Analytics programme is developing data science and AI focused on the process, structure, interactions and evolution of agents, technology and infrastructure within and between cities. With funding from the national UKRI initiative, AI for Science and Government (ASG), Leeds Turing Fellows now head up two projects under the Turing Digital Twins: Urban Analytics programme.


ASG-Turing Digital Twins: Urban Analytics

Synthetic population estimation and scenario projection model (SPENSER)

High resolution geographical and sub-population projections are essential for the planning and delivery of services and urban infrastructure developments. SPENSER (a synthetic population estimation and projection model) uses dynamic microsimulation to produce projections under different, user defined scenarios. Led by Turing Fellow Nik Lomax, SPENSER is making high resolution demographic forecasting accessible to stakeholders across a range of application areas, from physical infrastructure planning to health and social care spending and so facilitating evidence-based planning decisions.

Delivering Societal Impact through place-based urban analytics

A common feature of many UK cities is the juxtaposition of pockets of deprivation, reflected by significant disparities in life-expectancy and other key social and economic indicators, with wealthy and better resourced areas. This has led government policy-makers to consider more nuanced, ‘place-based’ analytical approaches to tackle the problems faced by these deprived areas.

This project will exploit an existing, linked dataset to enable LIDA data scientists to identify and explore the many interactions between health, education, activity (including travel) and social care in one of the UK’s most deprived areas – Bradford’s Holme Wood estate. The project is led by Turing Fellows Mark Mon-Williams and Faisal Mushtaq. In January 2020 the Turing Fellows led a workshop held at the Wolfson Centre for Applied Research in Bradford that brought together data scientists, community groups, practitioners and policy-makers, and identified a number of community priority issues that will be studied by the project (see ‘Turing Collaborative Events’ below) using urban analytics. The linked dataset will provide information to underpin a data-driven approach to informing service delivery, and present a platform for data science and AI to influence policy decisions in deprived areas across the UK.

ASG-Turing Criminal Justice System

A further AI for Science and Government project, under the Criminal Justice System programme, was launched in October 2019.

  • Computational models of police demand dynamics – Exploring how advanced simulation techniques might be used to increase understanding of demand for, and supply of, policing resources

The 21st century has seen increasingly diverse and novel responsibilities imposed upon the police service, while funding has declined. Limited policing resource has proved to be an enduring reality. The need to do more with less makes an understanding of short-, medium- and long-term demand a key priority. Without an increased understanding of the factors that drive demand, optimising police responses will continue to be a challenge. Led by Turing Fellow Dan Birks, this project aims to map the demand challenges and explore the viability of technical solutions in the form of simulation models that could support evidence-based ethical decision making. Learn more.


Turing Fellows and LIDA – Covid-19 research

LIDA data scientists and Turing Fellows are working hard on a number of research projects addressing the urgent need for scientific innovation to tackle the spread and effects of the COVID-19 pandemic.


Rapid Assistance in Modelling the Pandemic (RAMP)

Turing Programme Director for Urban Analytics and Director of LIDA, Professor Mark Birkin was tasked with leading a key work stream of The Rapid Assistance in Modelling the Pandemic (RAMP) initiative which is bringing modelling expertise from a diverse range of disciplines to support the pandemic modelling community working on the Coronavirus (COVID-19). Co-ordinated by the Royal Society, RAMP is helping to model the pandemic and guide the UK’s response. Professor Birkin is providing expertise to connect epidemic models to transport and urban analytics.


DECOVID project

The Alan Turing Institute DECOVID project is providing up to date information about patient care during the COVID-19 pandemic. This information will be analysed to answer the most pressing clinical questions to support the COVID-19 emergency response and to improve the quality of patient care for the future. A team of LIDA academics and researchers are contributing to the DECOVID Analytics work stream. Led by Turing Fellows Dave Westhead and Roy Ruddle, the LIDA team provide important expertise in the analysis of national data sets and machine learning in health care applications, and in data mining and visualization. Further expertise will be provided in areas such as epidemiology, electronic health records, ICU data and coding and causal inference methodology.


British Heart Foundation-Alan Turing Institute: Cardiovascular Data Science Award

Dr Marlous Hall and Dr Jianhua Wu have been awarded a British Heart Foundation-Alan Turing Institute Cardiovascular Data Science Award.

The aim of the award is to promote multi-disciplinary research to generate data science solutions to key cardiovascular problems, and will be used to investigate suitable methods to understand disease pathways following a heart attack at scale. Whilst a heart attack can be fatal, a large number of people do survive upon receipt of urgent medical care. Despite this, a heart attack can leave people at increased risk of developing further health conditions later in life. The full extent of which conditions are likely to develop following a heart attack, and in what timeframe, is unknown. Therefore, this project aims to study 145 million anonymised hospital records for patients across the whole of England to provide rich information on the temporal pathways of diseases which may follow a heart attack. However, the most appropriate methods needed to study such large volumes of data containing thousands of unique disease codes in a sequence at unstructured time intervals are not yet known. This pilot study will aim to investigate the most appropriate statistical and machine learning methods to do so. This will not only inform the wider research community, but also has the potential to provide detailed clinical evidence of the long term health consequences of a heart attack.


Turing Doctoral Students working with LIDA 2019/20

Sedar Olmez

Working with Turing Fellow, Alison Heppenstall, Sedar is focusing on data analytics and smart cities. He is developing a programming library designed to simulate how policies can impact a small world of autonomous intelligent agents to try to deduce positive or negative impact in the long run. Sedar plans to work on agent based modelling to solve and provide faster solutions to economic and social elements of society, establishing applied and theoretical answers.

Cécile de Bézenac

Cécile’s research, rooted in quantitative geography, is more specifically linked to urban studies. She is interested in developing prospective urban models that can assist policy-makers. Cécile is supervised by Turing Fellows Alison Heppenstall and Nick Malleson and is also a student of the Data Analytics & Society Centre for Doctoral Training.

Georgia Tomova

Georgia is a health data scientist whose main interest is using causal inference methods to improve health research, and specifically the field of nutrition. Supervised by Turing Fellows Peter Tennant and Mark Gilthorpe, Georgia’s research will involve evaluating the use of anthropometric composite variables commonly used in cardio-metabolic research for prediction and causal inference, such as body mass index, waist-to-hip ratio, and Metabolic Syndrome.


New Turing Interest Groups launched in 2019

Turing Interest Groups enable researchers and other interested parties to gather around shared areas of interest in data science and AI. Their aim is to spark new ideas for research collaboration and projects and to communicate emerging scientific concepts to wider audiences. The interest groups welcome new participants from outside the University.

During 2019/20 LIDA colleagues and Turing Fellows established three new interest groups:


Visualization Interest Group

Visualization has emerged in data science and AI as a fundamental technology, enabling human understanding of complex data and automated decision processes. There remains a challenge for visualization methods to keep pace with the scale and complexity of these activities. This needs research and innovation to create and deliver visualization tools that can continue to deliver technical, economic and social benefit. The Visualization Interest Group considers how we can gain insight into ever-growing datasets and see the reasoning behind automated AI decision-making. Turing Fellow and LIDA Deputy Director for Research, Professor Roy Ruddle, is a key organiser of the group.


Causal Inference Interest Group

Most analytical data science can be divided into three tasks; description, prediction, and causal inference. Description focuses on describing patterns and trends, often visually, in order to generally understand the occurrence of a concept of interest, e.g. how many people have diabetes; or how the risk of violent crime varies between areas. Prediction focuses on identifying patterns and forecasting possibilities, e.g. whether someone might develop a disease, or what the UK temperature might be in 2050. Causal inference focuses on determining how one thing influences another, and specifically focuses on estimating how changing one thing might change another, e.g. how does weight management affect the future risk of diabetes; how would the risk of violent crime change if a minimum unit price of alcohol was introduced?

Organisers of the Causal Inference Interest Group include Turing Fellow and University Academic Fellow in Health Data Science, Peter Tennant; Turing Fellow and Professor of Statistical Epidemiology, Mark Gilthorpe; and Turing Postgraduate Researcher, Georgia Tomova.


Best Practice for Collecting Cybersecurity Data Interest Group

This Interest Group was established by Turing Fellow and Professor of Criminology in the School of Law, David Wall, in collaboration with colleagues from Newcastle University. The group will bring key data stakeholders together with Data Scientists and AI experts in order to organise and develop best practices around collecting cybersecurity data. It will seek to develop standards for collecting, and for analysing and using the data in ways that are both ethically safe, minimal in bias, and also useful for building insights into how all organisations (public, private and third sector) can be made more cybersecure in the future.


Turing collaborative events 2019-2020

Delivering Societal Impact through place-based urban analytics

In January, 120 data scientists, policy makers, service providers and community activists met at the Wolfson Centre for Applied Research in Bradford at a special workshop funded by the Alan Turing Institute.  Their purpose was to begin the conversation on how cutting-edge data science could be used to improve our understanding of sub-city level inequalities, to better inform the development of policy within and across sectors including education, health, social care and transport, and so have a real impact on the quality of people’s lives. Led by Turing Fellows, Mark Mon–Williams and Faisal Mushtaq, the workshop centred around the post-war Holme Wood estate located to the south of Bradford City centre. The discussions identified several priority issues for Holme Wood that are now being studied using urban analytics (see ‘New Research’ above). Following the workshop a series of reports have been written and it is anticipated that the work will inform a wider national debate about the use of data in policy-making within Local and Central Government.

Jon Rowe visit to LIDA

Turing Programme Director, Data Science for ScienceProfessor Jon Rowe from the University of Birmingham visited LIDA in March 2020. He discussed potential collaborations with researchers from the Faculty of Environment interested in research areas such as AI methods to project future ice sheet instabilities. His presentation “The data science revolution in scientific research” was given as part of the LIDA seminar series.

Back to annual review