Population Displacement During Disasters Predicted Using Mobile Data

Using data supplied by a mobile operator, researchers at Karolinska Institutet have shown that population movements after the 2010 Haiti earthquake followed regular patterns. This information can be used to predict beforehand the movements of people after a disaster, and thus improves chances for aid to be delivered to the right places at the right time.

Every year, tens of millions of people are displaced by natural disasters, and to date knowledge of their movement patterns has been sparse. The results of the study, now published in The Proceedings of the National Academy of Sciences (PNAS), could therefore help aid organisations to prepare and execute their relief efforts following a major disaster.

After the earthquake in Haiti, over 600,000 people left the capital Port-au-Prince, and over a million people were left homeless. With the help of mobile data provided by Digicel, the largest mobile operator in Haiti, the researchers looked for patterns in the movements of two million anonymous mobile users.

"When disaster strikes we tend to seek comfort in our nearest and dearest," says Xin Lu, who conducted the study together with colleagues Dr Linus Bengtsson and Dr Petter Holme. "We can see by the mobile data that where people were over Christmas and New Year, which was just before the earthquake, tended to be the place where they returned to afterwards."

The team also studied the everyday movements of people and found that although people moved greater distances after the earthquake compared to before, their daily movement patterns were extremely regular. Knowing a person's movements during the first three months after the earthquake, the researchers were able to show that it is possible to predict with 85 per cent probability the location of this person on a particular day in the ensuing period.

The researchers led the work on a paper last August where they, together with colleagues, showed how mobile data could be used to describe population movements after a disaster has happened. This present study takes the work a step further by showing the potential to predict population movements beforehand. Since the disaster, Linus Bengtsson and Xin Lu, both doctoral students at Karolinska Institutet's Division of Global Health, have initiated Flowminder.org, a non-profit organisation with the aim of disseminating analyses of population movements for free to relief agencies after disasters.

Xin Lu, Linus Bengtsson & Petter Holmen
Predictability of population displacement after the 2010 Haiti earthquake
PNAS, online first 18-22 June 2012

Most Popular Now

Transforming Drug Discovery with AI

A new AI-powered program will allow researchers to level up their drug discovery efforts. The program, called TopoFormer, was developed by an interdisciplinary team led by Guowei Wei, a Michigan...

We may Soon be Able to Detect Cancer wit…

A new paper in Biology Methods & Protocols, published by Oxford University Press, indicates that it may soon be possible for doctors to use artificial intelligence (AI) to detect and...

Health Innovation East Partners with Cog…

Health Innovation East, the innovation arm of the NHS in the East of England and Cogniss, a no-code ecosystem for digital health solutions, have announced a strategic partnership to launch...

New Computational Model of Real Neurons …

Nearly all the neural networks that power modern artificial intelligence (AI) tools such as ChatGPT are based on a 1960s-era computational model of a living neuron. A new model developed...

Meet CARMEN, a Robot that Helps People w…

Meet CARMEN, short for Cognitively Assistive Robot for Motivation and Neurorehabilitation - a small, tabletop robot designed to help people with mild cognitive impairment (MCI) learn skills to improve memory...

AI Matches Protein Interaction Partners

Proteins are the building blocks of life, involved in virtually every biological process. Understanding how proteins interact with each other is crucial for deciphering the complexities of cellular functions, and...

AI Model to Improve Patient Response to …

A new artificial intelligence (AI) tool that can help to select the most suitable treatment for cancer patients has been developed by researchers at The Australian National University (ANU). DeepPT, developed...

Mobile Phone Data Helps Track Pathogen S…

A new way to map the spread and evolution of pathogens, and their responses to vaccines and antibiotics, will provide key insights to help predict and prevent future outbreaks. The...

Think You're Funny? ChatGPT might b…

A study comparing jokes by people versus those told by ChatGPT shows that humans need to work on their material. The research team behind the study published on Wednesday, July 3...

Can AI Tell you if You Have Osteoporosis…

Osteoporosis is so difficult to detect in early stage it’s called the "silent disease." What if artificial intelligence could help predict a patient’s chances of having the bone-loss disease before...

Study Reveals Why AI Models that Analyze…

Artificial intelligence (AI) models often play a role in medical diagnoses, especially when it comes to analyzing images such as X-rays. However, studies have found that these models don’t always...

Innovative, Highly Accurate AI Model can…

If there is one medical exam that everyone in the world has taken, it's a chest x-ray. Clinicians can use radiographs to tell if someone has tuberculosis, lung cancer, or...