Abstract
Data collected at large scale and low cost (e.g. satellite and street level imagery) have the potential to substantially improve resolution, spatial coverage, and temporal frequency of measurement of urban inequalities. Multiple types of data from different sources are often available for a given geographic area. Yet, most studies utilize a single type of input data when making measurements due to methodological difficulties in their joint use. We propose two deep learning-based methods for jointly utilizing satellite and street level imagery for measuring urban inequalities. We use London as a case study for three selected outputs, each measured in decile classes: income, overcrowding, and environmental deprivation. We compare the performances of our proposed multimodal models to corresponding unimodal ones using mean absolute error (MAE). First, satellite tiles are appended to street level imagery to enhance predictions at locations where street images are available leading to improvements in accuracy by 20, 10, and 9% in units of decile classes for income, overcrowding, and living environment. The second approach, novel to the best of our knowledge, uses a U-Net architecture to make predictions for all grid cells in a city at high spatial resolution (e.g. for 3 m × 3 m pixels in London in our experiments). It can utilize city wide availability of satellite images as well as more sparse information from street-level images where they are available leading to improvements in accuracy by 6, 10, and 11%. We also show examples of prediction maps from both approaches to visually highlight performance differences.
Highlights
Over half of the global population is currently urban, with urban areas projected to absorb all future population growth
We demonstrate our methods on satellite and street level imagery from London where the aim is to predict income, overcrowding, and environmental deprivation at high spatial resolution and coverage
We report the averages of the four cross validation runs along with minimum and maximum values for each outcome
Summary
Over half of the global population is currently urban, with urban areas projected to absorb all future population growth. As cities adapt to growth in population and increasing density, challenges and conflicts emerge regarding provision of services, such as adequate and affordable housing and access to health care, leading to increasing and dramatic levels of inequality. Emerging sources of large-scale data, such as remote sensing, street-level imagery, mobile phones, and crowd-sourced data, coupled with advances in deep learning methods, have the potential to signifi cantly advance the speed, frequency and spatial precision of the measurement of urban characteristics. Such advances may help identify specific areas of concern at earlier stages, so that interventions can be more quickly implemented through targeting policies to areas of greatest need
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
