气候变化领域集成服务门户(CCPortal): Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas

CCPortal

DOI	10.1016/j.rse.2021.112339
	Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas
	Suel E.; Bhatt S.; Brauer M.; Flaxman S.; Ezzati M.
发表日期	2021
ISSN	00344257
卷号	257
英文摘要	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. © 2021 The Author(s)
英文关键词	Convolutional neural networks; Satellite images; Segmentation; Street-level images; Urban measurements
语种	英语
scopus关键词	Forecasting; Image enhancement; Satellite imagery; High spatial resolution; Learning-based methods; Living environment; Mean absolute error; Multimodal models; NET architecture; Satellite images; Temporal frequency; Deep learning; machine learning; satellite imagery; spatial resolution; urban area
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/178905
作者单位	MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, United Kingdom; Swiss Data Science Center, ETH Zurich and EPFL, Switzerland; MRC Centre for Global Infectious Disease Analysis, School of Public Health, Imperial College London, London, United Kingdom; Section of Epidemiology, Department of Public Health, University of Copenhagen, Denmark; Abdul Latif Jameel Institute for Disease and Emergency Analytics, Imperial College London, London, United Kingdom; School of Population and Public Health, University of British Columbia, Vancouver, BC, Canada; Institute for Health Metrics & Evaluation, University of Washington, Seattle, WA, United States; Department of Mathematics, Imperial College London, London, United Kingdom; Regional Institute for Population Studies, University of Ghana, Accra, Ghana
推荐引用方式 GB/T 7714	Suel E.,Bhatt S.,Brauer M.,et al. Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas[J],2021,257.
APA	Suel E.,Bhatt S.,Brauer M.,Flaxman S.,&Ezzati M..(2021).Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas.Remote Sensing of Environment,257.
MLA	Suel E.,et al."Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas".Remote Sensing of Environment 257(2021).