Dr Nick Malleson

Profile

I am a Professor of Spatial Science at the Institute for Spatial Data Science (ISDS) at the School of Geograph. My research leverages techniques developed in computer science, statistics and machine learning, and applies them to critical social problems that have a strong geographical context. I am best known for my work on agent-based modelling (an individual-level simulation approach) and in the development of machine-learning and geographical information science techniques to solve problems in the domains of criminal justice, mobility and health.

For the latest research updates see:

• My personal research website
• The ERC dust project.
• The surf project

Employment history

• Apr 2019 – present. Professor of Spatial Science, University of Leeds.
• July 2012 – Apr 2018. Lecturer & Associate Professor in GISc, University of Leeds.
• Feb 2010 – July 2012. Research fellow, University of Leeds.
• Oct 2006 – Feb 2010. ESRC-funded doctoral student with lecturing duties, University of Leeds. Sept 2005 – Aug 2006. Masters student, University of Leeds.
• Sept 2002 – Aug 2005. Undergraduate student, University of Leeds.

Major Grants & Prizes

• Royal Geography Society (RGS) Gill Memorial Award for outstanding early career research in agent-based social geography [geocomputation]. (Further details).
• €1.5M (£1.3M) ERC Starting Grant entitled Data Assimilation for Agent-Based Models (dust.leeds.ac.uk/).
• £312k ESRC Future Research Leaders grant entitled Understanding Urban Movements through Big Data and Social Simulation (surf.leeds.ac.uk/).

Responsibilities

• Cluster Leader: Institute for Spatial Data Science

Research interests

Data Assimilation for Agent-Based Modelling (dust)

This 5-year research project, which is being funded by the European Research Council, will develop dynamic data assimilation methods for use in agent-based modelss.

surf - Simulating Urban Flows

The aim of the surf project is to create a simulation that is capable of modelling the individual movements of people in an urban environment as they undertake their daily routine activities (commuting, shopping, schooling, etc.). It will use a combination of 'big data' analysis and cutting-edge computer simulation to create a highly realistic siulation that we can use to better undestand the daily ebb and flow of urban life. Ultimately, the results will be used to quantify the impacts of levels of crime and pollution on citizens

Consumer Data Research Centre (CDRC)

The aim of the CDRC is to create, supply, maintain and deliver consumer-related data to a range of end users, alongside a programme of research and outreach activities. I am leading a research strand that will apply advanced spatial analysis and modelling techniques to reveal new insights into the causes and distributions of crime through the inclusion of novel ‘Big’ data sources.

N8 Policing Research Partnership: Innovation and the Application of Knowledge for More Effective Policing

This 5 year project will develop and test mechanisms of research co-production between the Police and Universities. I am involved in the Policing Data Analytics strand, that will look at new ways to safely access and analyse police and crime data.

GeoCrimeData: Exploring Geospatial Data for Crime Analysis

The work of crime analysts and modellers could benefit substantially from the use of new spatial data sets that are becoming more readily available. Examples include road networks (e.g. Open Street Map), building boundary datasets (e.g Ordnance Survey MasterMap) as well as under-utilised social network data (e.g. Twitter) or other volunteered sources. The GeoCrimeData Project is exploring many novel data sources and manipulating them using geographical routines in order to generate new forms of spatial intelligence that can help to add value to the interpretation of recorded crime data

Agent-Based Modelling of Crime

Crime is an extremely complex phenomenon which is driven by a wide array of both environmental and human-behavioural characteristics. Traditional techniques which utilise statistical methods to investigate crime and predict future crime rates struggle to incorporate the highly detailed, low-level factors which will determine whether or not a crime is likely to occur.

This research utilises agent-based modelling which is a methodology that can account for these low-level characteristics. By incorporating detailed behavioural information into a simulation consisting of many 'intelligent' agents it might be possible to produce hypotheses regarding how offenders behave in the real world and the factors which determine their movements.

The product of the work will be an application which could be used by local authorities to predict the effects of new environmental developments or policies. Specifically, the model will be used to experiment with the effects that a major development project will have on rates of residential burglary in Leeds.

• Integrated Analysis of Social Media and Hedonic House Prices for Neighbourhood Change (INTEGRATE)
• Reconceptualising climate impacts from the bottom-up: An ethnoclimatology of climate risk (ETHNO-CLIM)

Qualifications

• PhD, School of Geography, University of Leeds
• MSc, Multidisciplinary Informatics, University of Leeds
• BSc, Computer Science, University of Leeds

Research groups and institutes

• Institute for Spatial Data Science

Current postgraduate researchers

• Sedar Olmez
• Raidah Hanifah