Professor Alison Heppenstall
- Professor of Geocomputation (Urban Studies)
Biography
My PhD (University of Leeds) was a mixture of spatial econometrics and artificial intelligence, specifically building agent-based models to replicate dynamics within a retail market (petrol prices). Subsequent EPSRC and ESRC Fellowships focused on the building of Machine Learning approaches such as neural networks and evolutionary algorithms for both flood and water quality prediction. My academic career has focused on working with individual-based approaches, both microsimulation and agent-based modelling. I am interested in the methodological developments around individual-based models. These include uncertainty quantification, probabilistic programming, graph theory, deep learning, reinforcement learning, emulators, particle filters, neural networks etc
Whilst at the University of Leeds, I was involved in the Leeds Institute for Data Analytics, Consumer Data Research Centre and the Urban Analytics Programme at the Alan Turing Institute. I held an ESRC-Turing Fellowship and continue to work on urban digital twins with the Turing. I am a member of the DSAB at the Joint BioSecurity Council and a member of the Royal Geographical Society.
I work across both COSS and the MRC Unit at the University of Glasgow.
Research interests
My research interests span a wide range of ML and AI approaches including uncertainty quantification, probabilistic programming, graph theory, deep learning, reinforcement learning, emulators, particle filters, neural networks etc. I work within health and sustainability to understand the impact of net zero policies on health inequalities.
Grants
Systems Science in Public Health and Health Economics Research (SIPHER) : SIPHER vision is a shift from health policy to health public policy. Along with Dr Nik Lomax, I am responsible for the data management and micro-modelling work streams of this 5 year UKPRP consortium
Behavioural, ecological and socio-economic tools for modelling agricultural policy (BESTMAP - H2020): My role in this project is to devise ways to scale up ABMs from local to national levels.
Consumer Data Research Centre (ESRC):The CDRC seeks to develop new approaches to social science research which are needed to exploit new sources of consumer data. I hold the post of Director of Innovation.
Understanding and Quantifying Uncertainty in Agent-Based Models for Smart City Forecasts: (Turing) Developing methods that can be used to better understand uncertainty in individual-level models of cities
Capturing relationships between individuals: Integrating Causal Inference and Agent-based modelling: (Turing). This project will connect ongoing work in casual inference modelling to agent-based simulations to robustly capture and simulate causal relationships between individuals.
Forecasting the future of policing (Turing): This project is in conjunction with UCL and The Met to explore the potential of ABM as a tool for forecasting demands in policing. The PI is Dr Dan Birks (University of Leeds).
Quantifying Utility and Preserving Privacy in Synthetic Data (QUIPP): This is a joint project with the Turing that is aims to generate synthetic versions of sensitive data sets that contain all the relationships and preserve individual privacy.
Supervision
- Feng, Zixin
Exploring the Electric Vehicle Driver Behaviours for the Sustainable Future of Charging Infrastructure