Alison Heppenstall is Professor of Geocomputation at the University of Leeds and an ESRC-Turing Fellow. She has a PhD in Artificial Intelligence, a focus of which was developing machine learning algorithms (e.g. neural networks) and AI approaches (agent-based models) that were applied to solving complex spatial problems. Most of her current research is focused on developing and adapting machine learning approaches to understanding social phenomena. She has particular interests in data analytics, developing approaches for detecting 'hidden' spatio-temporal patterns in 'big data', quantifying uncertainty in simulations, and building more robust individual-based models through probabilistic programming and reinforcement learning.

Research interests

Professor Heppenstall is involved in several strands of work at the Turing. Her ESRC-Turing Fellowship is focused on (i) developing new ML tools for detecting hidden patterns and structures within cities and (ii) creating robust agent-based modelling simulations for Smart Cities, for example understanding the impact of new infrastructure or air pollution.  

Professor Heppenstall is also involved in the two other Turing-funded projects: the first project will develop methods that can be used to better understand uncertainty in individual-level models. In particular, it will explore and extend the state-of-the-art in two related areas: ensemble modelling and emulators for use in individual-level models. The second project will investigate linking together casual inference modelling with agent-based modelling. Can we improve our agent-based models through a better understanding of the relationships in large, dynamic data sets?

Achievements and awards

Professor Heppenstall holds an ESRC-Turing Fellowship.