Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Urban Informatics and Future CitiesHow Various Natural Disasters Impact Urban Human Mobility Patterns: A Comparative Analysis Based on Geotagged Photos Taken in Tokyo

Urban Informatics and Future Cities: How Various Natural Disasters Impact Urban Human Mobility... [This study analyzed the impacts of various extreme natural events that affected Tokyo’s human movement patterns between 2008 and 2019 based on geotagged photos shared online. First, we selected six disasters of different types according to severity, damage, and photo count. Next, we delineated three phases representing steady and perturbed conditions (before, during, and after) for each extreme event based on relevant weather measurements. We then analyzed human mobility patterns via two indicators: displacement and mean squared displacement (MSD). A transfer-learning-based convolutional neural network (CNN) model was also developed to classify the photos according to whether they were taken indoors or outdoors. Thus, we analyzed the characteristics of people’s trips within and between the two environments. The results show that, while all extreme events perturbed mobility patterns to different degrees, these patterns mostly followed a truncated power-law distribution during steady and unsteady states.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Urban Informatics and Future CitiesHow Various Natural Disasters Impact Urban Human Mobility Patterns: A Comparative Analysis Based on Geotagged Photos Taken in Tokyo

Part of the The Urban Book Series Book Series
Editors: Geertman, S. C. M.; Pettit, Christopher; Goodspeed, Robert; Staffans, Aija

Loading next page...
 
/lp/springer-journals/urban-informatics-and-future-cities-how-various-natural-disasters-vTEtxeIiZs
Publisher
Springer International Publishing
Copyright
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021
ISBN
978-3-030-76058-8
Pages
151 –171
DOI
10.1007/978-3-030-76059-5_9
Publisher site
See Chapter on Publisher Site

Abstract

[This study analyzed the impacts of various extreme natural events that affected Tokyo’s human movement patterns between 2008 and 2019 based on geotagged photos shared online. First, we selected six disasters of different types according to severity, damage, and photo count. Next, we delineated three phases representing steady and perturbed conditions (before, during, and after) for each extreme event based on relevant weather measurements. We then analyzed human mobility patterns via two indicators: displacement and mean squared displacement (MSD). A transfer-learning-based convolutional neural network (CNN) model was also developed to classify the photos according to whether they were taken indoors or outdoors. Thus, we analyzed the characteristics of people’s trips within and between the two environments. The results show that, while all extreme events perturbed mobility patterns to different degrees, these patterns mostly followed a truncated power-law distribution during steady and unsteady states.]

Published: Jul 16, 2021

Keywords: Human mobility; Natural disasters; Flickr; Geotagged photos; Convolutional neural network; Tokyo; Japan

There are no references for this article.