59
IRUS Total
Downloads

Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas

File Description SizeFormat 
1-s2.0-S0034425721000572-main.pdfPublished version7.51 MBAdobe PDFView/Open
Title: Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas
Authors: Suel, E
Bhatt, S
Brauer, M
Flaxman, S
Ezzati, M
Item Type: Journal Article
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.
Issue Date: 1-May-2021
Date of Acceptance: 1-Feb-2021
URI: http://hdl.handle.net/10044/1/87597
DOI: 10.1016/j.rse.2021.112339
ISSN: 0034-4257
Publisher: Elsevier
Journal / Book Title: Remote Sensing of Environment: an interdisciplinary journal
Volume: 257
Copyright Statement: © 2021 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
Sponsor/Funder: Medical Research Council (MRC)
Engineering & Physical Science Research Council (EPSRC)
The Academy of Medical Sciences
Wellcome Trust
UK Research and Innovation
Funder's Grant Number: MR/S003983/1
EP/V002910/1
SBF004/1080
209376/Z/17/Z
MR/V038109/1
Keywords: Science & Technology
Life Sciences & Biomedicine
Technology
Environmental Sciences
Remote Sensing
Imaging Science & Photographic Technology
Environmental Sciences & Ecology
Convolutional neural networks
Segmentation
Urban measurements
Satellite images
Street-level images
Geological & Geomatics Engineering
0406 Physical Geography and Environmental Geoscience
0909 Geomatic Engineering
Publication Status: Published
Article Number: ARTN 112339
Online Publication Date: 2021-02-23
Appears in Collections:Mathematics
Statistics
School of Public Health
Faculty of Natural Sciences



This item is licensed under a Creative Commons License Creative Commons