Recent years have witnessed a growth of urban environments, with more than half of the world's population living in urban areas. Cities are developing at an unprecedented pace and are becoming hubs of innovation, social interactions, economic growth and globalisation. However, this rapid growth and development also leads to new challenges to better understand economic inequalities in cities, crime, sustainability and the wellbeing of people living in urban environments. Traditionally, quantitative studies of cities have faced several challenges, such as inadequate data on the multifaceted nature of urban environments. The recent availability of large data sets derived from our interactions with large technological systems, such as the Internet and the mobile phone network, offers novel opportunities in the area of urban analytics.
We all regularly use mobile phones and social media platforms for social interactions, and this generates a vast amount of data on our behaviour and our mobility. At the same time, large scale open collaborative projects such as OpenStreetMap and Geograph are now available to study urban environments at very high spatial resolution. An increasing amount of research studies have explored how we can use these new forms of data to measure our society, our cities and how people perceive them. Recent developments in artificial intelligence and deep learning techniques have even allowed us to better understand how cities look and what makes them beautiful.
The aim of this project is to build on previous studies and novel sources of data to quantitatively study urban environments, with a particular focus on human behaviour. Using tools from data science, complex networks and computational social science, this project will explore how urban environments relate to the people living there, and how we can better understand the cities we live in. Throughout their PhD, the student will tackle challenges in the study of urban systems, such as understanding mobility with mobile phone data, or producing socioeconomic indicators based on publicly available data. In particular, the student will likely be working with statistical methods for the analysis of large data sets, spatial modelling techniques and develop code in a modern programming language, such as Python or R.
This is an interdisciplinary project which will allow the student to develop skills at the intersection between several disciplines which are relevant to both academia and industry. The supervisory team has broad experience in working across disciplines and collaborating with policy makers, NGOs and private companies.
Please contact Dr. Federico Botta informally for more details by email at [Email Address Removed].