Maynooth University Faculty of Social Sciences

As a spatial data scientist and urban geographer, my research is focused broadly on better understanding how urban spatial structure and transportation systems influence economic, environmental, and social outcomes in order to help solve the complex ongoing crises facing our interconnected global society in the 21st century: economic inequality, climate change, widespread health disparities, and other forms of social, racial, and environmental injustice. Cities are complex systems, and their spatial organisation has a direct impact on basically every feature of human life: how our economy functions, how new ideas are generated, how people have access to jobs, how they interact with their friends and strangers, how they get exercise, how they get their food, how they vote, and how much they pollute – and the decisions that city governments make (or don’t make) thus have far-reaching impacts on people’s health, economic behaviour, and relative social advantage or disadvantage.

I study these topics mostly using quantitative, data-driven approaches because I believe that “data is power,” and although all policy decisions inherently occur in a political framework (and structural political change is certainly a prerequisite for solving these complex problems), quantitative data and statistical analysis – when properly applied and understood – can provide powerful evidence in favour of particular policies that can foster beneficial change in the world. To make change, we always need to know the empirical situation: the drivers, consequences, and outcomes of urban spatial structure and planning policies. And as the data and methods used to characterise the empirical situation become more complex, we need to likewise sharpen our understanding and interpretation of these data and methods, which includes understanding how spatial ways of thinking and explicitly spatial methodological approaches can be used to analyse large datasets and can be better integrated into conventional statistical and newer machine learning methods.

Specifically, my recent research focuses on understanding how machine learning (ML) and artificial intelligence (AI) approaches can be designed to: 1) more explicitly integrate spatial information and spatial ways of thinking, 2) assess problems of causal inference, and 3) provide better insight into the explanatory relationships driving model results. I am currently working on a range of projects in this area, including: developing causal machine learning models for spatial data, designing a community-focused health + environment spatial data dashboard for the Dublin 8 neighbourhood, developing an AI tool to help increase building energy retrofit uptake, and analysing non-auto commuting patterns in Dublin. I am an Affiliate Member of the Maynooth University Hamilton Institute (2022), an Academic Collaborator at the ADAPT Centre for Digital Media Technology in the Digital Content Transformation (DCT) Strand (2022), a Fellow of the Center for Spatial Data Science at the University of Chicago (2021), and received my PhD in Geography from Michigan State University in 2018. 

Follow me on BlueSky @kevincredit.bsky.social for periodic research updates, GitHub for code implementations, and check out my profiles on Planetizen (where I have taught courses on location optimisation), Google Scholar, ResearchGate, and LinkedIn.