Modelling urban vibrancy with mobile phone and OpenStreetMap data

Abstract

The concept of urban vibrancy has become increasingly important in the study of cities. A vibrant urban environment is an area of a city with high levels of human activity and interactions. Traditionally, studying our cities and what makes them vibrant has been very difficult, due to challenges in data collection on urban environments and people's location and interactions. Here, we rely on novel sources of data to investigate how different features of our cities may relate to urban vibrancy. In particular, we explore whether there are any differences in which urban features make an environment vibrant for different age groups. We perform this quantitative analysis by extracting urban features from OpenStreetMap and the Italian census, and using them in spatial models to describe urban vibrancy. Our analysis shows a strong relationship between urban features and urban vibrancy, and particularly highlights the importance of third places, which are urban places offering opportunities for social interactions. Our findings provide evidence that a combination of mobile phone data with crowdsourced urban features can be used to better understand urban vibrancy.

Fig 1. Presence of mobile phone users and density of urban features in Milan.

We retrieve data on the number of mobile phone users in the city of Milan, together with their age group, as derived from Telecom Italia data between March and April 2015. (A) Mobile phone users are provided for cells in a discrete grid superimposed on the city. We depict here all the cells which are included in the dataset for the metropolitan city of Milan. (B) Our analysis focuses on urban environments in densely populated areas. We present here the geographical boundaries of the administrative unit of the metropolitan city of Milan, which we use to select those cells in the data set which are part of the large urban area of Milan. (C, D) We depict here the average density of users for two different age groups across the area of analysis. Visual inspection suggests that the overall pattern is consistent across the two groups (E, F) We compare the presence of people across the city with the underlying urban structure of the different cells. To quantify the urban environment, we consider data derived from OpenStreetMap (OSM) and the Italian census. Here, we present (E) the number of road intersections extracted from OSM, and (F) the vertical density of buildings. All maps in this Figure are oriented North.

Fig 2. Relationship between presence of people and geographic features.

In these scatter plots each point represents a cell in each city. The x-axis encodes the presence of all age groups aggregated together, whereas the y-axis represents the values for each feature described in the Data section. All quantities are normalised by the area of the cell. The points are plotted with some transparency so that accumulation of multiple cells with similar values looks slightly darker.

Fig 3. Age group differences in an univariate spatial error model of geographical features.

For each city and each age group we run a univariate spatial regression model where the dependent variable Y is the vibrancy, and the independent variable X is one urban feature at a time. We first run the the spatial error model for the aggregate case (all ages) and then subtract the resulting coefficient from each age group. Thus, a positive value for a certain age group indicates that a particular urban feature is relatively more strongly related to the vibrancy compared to the aggregate case. X and Y axes are all the same across small multiples, and labels are only displayed in the bottom-right subplot. Before running the univariate linear model, all values have been standardised subtracting the mean and dividing by the standard deviation. Straight lines along zero indicate no variation across age groups. The error bars are provided by the spatial model result. The grey bands around zero indicate the error of the aggregate value. Milan, Rome and Turin are the cities with higher number of cells (and populations) and more significant patterns. An equivalent plot using the spatial lag model can be found in the S1 File.

Fig 4. Age group differences in an univariate spatial error model of third places.

For each city and each age group we run a univariate spatial error model where the dependent variable Y is the vibrancy, and the independent variable X is one of the categories of third places at a time. Similar to Fig 3, we firstly run the same model for the aggregated case (all ages) and subtract the resulting coefficient from each age group. X and Y axes are all the same across small multiples, and labels are only displayed in the bottom-right subplot. All values have been standardised subtracting the mean and dividing by the standard deviation before running the univariate model. Straight lines along zero indicate no variation across age groups. The error bars are provided by the spatial model result. The grey bands around zero indicate the error of the aggregate value. Milan, Rome and Turin are the cities with higher number of cells (and populations) and more significant patterns. An equivalent plot using the spatial lag model can be found in the S1 File.