Machine Learning

Measuring Urban Forest Using Street-Level Imagery and Deep Learning

We develop a method based on computer vision and a hierarchical multilevel model to derive an Urban Street Tree Vegetation Index which aims to quantify the amount of vegetation visible from the point of view of a pedestrian. Our approach unfolds in two steps. First, areas of vegetation are detected within street-level imagery using a state-of-the-art deep neural network model. Second, information is combined from several images to derive an aggregated indicator at the area level using a hierarchical multilevel model. The comparative performance of our proposed approach is demonstrated against a widely used image segmentation technique based on a pre-labelled dataset. The approach is deployed to a real-world scenario for the city of Cardiff, Wales, using Google Street View imagery. Based on more than 200,000 street-level images, an urban tree street-level indicator is derived to measure the spatial distribution of tree cover, accounting for the presence of obstructing objects present in images at the Lower Layer Super Output Area (LSOA) level, corresponding to the most commonly used administrative areas for policy-making in the United Kingdom. The results show a high degree of correspondence between our tree street-level score and aerial tree cover estimates. They also evidence more accurate estimates at a pedestrian perspective from our tree score by more appropriately capturing tree cover in areas with large burial, woodland, formal open and informal open spaces where shallow trees are abundant, in high density residential areas with backyard trees, and along street networks with high density of high trees. The proposed approach is scalable and automatable. It can be applied to cities across the world and provides robust estimates of urban trees to advance our understanding of the link between mental health, well-being, green space and air pollution.

Career trajectories and outcomes of forced migrants in Sweden. Self-employment, employment or persistent inactivity?

We examine the career pathways of forced migrants using sequence analysis from their arrival in 1991 through to 2013.

Understanding and Predicting the Long-term Labour Market and Migration Trajectories of Immigrants and Their Children in the United Kingdom

This project aims to investigate how the educational and employment trajectories of immigrants and their children in the UK evolve and interact; and, how factors related to their residential environment, early life context and critical life transitions shape these trajectories between 1991-2017.

Using large scale social media data to measure perceptions towards immigration

This project aims to develop analytical methods to analyse perceptions towards immigration using twitter data and machine learning

A Hierarchical Urban Forest Index Using Street-Level Imagery and Deep Learning

We develop a method based on computer vision and a hierarchical multilevel model to derive an Urban Street Tree Vegetation Index which aims to quantify the amount of vegetation visible from the point of view of a pedestrian.

Estimating Global Bilateral Migration Flows

This project aims to generate annual country-to-country migration estimates across the world.

Using satellite imagery to measure the evolution of cities

The project aims to develop and employ analytical approaches to measure the evolution of cities using machine learning and satellite imagery.

The returns to migration and human capital accumulation pathways. non-metropolitan youth in the school-to-work transition

This paper examines the influence of migration and school-to-work pathways on entry-level wages for non-metropolitan youth in Australia.