As part of our “Research Bites” series, in which we ask data science researchers to spend five minutes telling us in their own words about their work, and opportunities for practical applicability in the context of sustainable development or humanitarian action, today we hear from researchers Xuan Song, Quanshi Zhang, Yoshihide Sekimoto and Ryosuke Shibasaki from the Center for Spatial Information Science at the University of Tokyo.
Prediction of Human Emergency Behavior and their Mobility following Large-scale Disaster
The frequency and intensity of natural disasters has significantly increased over the past decades and this trend is predicted to continue. Facing these possible and unexpected disasters, accurately predicting human emergency behavior and their mobility will become a critical issue for planning effective humanitarian relief, disaster management, and long-term societal reconstruction. In this paper, researchers built a large human mobility database (GPS records of 1.6 million users over one year) and several different datasets to capture and analyze human emergency behavior and their mobility following the Great East Japan Earthquake and Fukushima nuclear accident. In addition, they developed a model to accurately predict human emergency behavior and their mobility should a similar large-scale disaster happen in the future. The experimental results suggest that human behavior and their movements during disasters may be significantly more predictable than previously thought.
The full research paper can be accessed online here and more information on the research effort at: http://shiba.iis.u-tokyo.ac.jp/song/?page_id=50
1. Tell us about your research paper in two sentences
In this research, we used big data (GPS records of 1.6 million users throughout Japan over one year) to analyze and model human mobility following the Great East Japan Earthquake and Fukushima nuclear accident. We are trying to develop a model to accurately predict human emergency behavior and their mobility, should a similar large-scale disaster happen in the future.
2. Why do your findings matter?
The frequency and intensity of natural disasters has significantly increased over the past decades and this trend is predicted to continue. Facing these possible and unexpected disasters, accurately predicting human emergency behavior and their mobility will become a critical issue for planning effective humanitarian relief, disaster management, and long-term societal reconstruction.
3. How could this research be put into practice?
This research is supported by the Government of Japan, and we also have extensive collaborations with the industrial community of Japan. By now, we have implemented several intelligent systems for disaster behavior analysis, reasoning, and urban emergency management. We will try to have the systems serve Japanese society as soon as possible.
4. Why did you select this topic to research?
Japan is one of the countries most affected by natural disasters. Two out of the five most expensive natural disasters (Great Hanshin Earthquake and Great East Japan Earthquake) in recent history have occurred in Japan, resulting in a large number of deaths, injuries and huge economic loss. Japan has also been the site of some of the worst natural disasters of the 21st century. Facing these unexpected disasters, it is very important to record people’s movements following the event to analyze their behavioral patterns and to develop simulation or predictive models for future disaster mitigation. In addition, the types of data, evacuation behavior pattern, and simulation model available following the Great East Japan Earthquake and the Fukushima Daiichi nuclear power plant meltdown are unique in human history, and are likely to play a vital role in future disaster relief and management worldwide.
The researchers will be on hand to answer questions in the comments section below, so we invite practitioners from the development or humanitarian sectors to join the discussion!
Twitter: Center for Spatial Information Science, University of Tokyo @CSISut
