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

Specially Designed Video Games may Benef…

In a review of previous studies, a Johns Hopkins Children's Center team concludes that some video games created as mental health interventions can be helpful - if modest - tools...

AI may Enhance Patient Safety

Generative artificial intelligence (genAI) uses hundreds of millions, sometimes billions, of data points to train itself to produce realistic and innovative outputs that can mimic human-created content. Its applications include...

AI Chatbots Rival Doctors in Accuracy fo…

A new study reveals that artificial intelligence chatbots, such as ChatGPT, may be almost as effective as consulting a doctor for advice on low back pain. Conducted by an international team...

Researchers Harness AI to Repurpose Exis…

There are more than 7,000 rare and undiagnosed diseases globally. Although each condition occurs in a small number of individuals, collectively these diseases exert a staggering human and economic toll because...

Paving the Way for New Treatments

A University of Missouri researcher has created a computer program that can unravel the mysteries of how proteins work together - giving scientists valuable insights to better prevent, diagnose and...

AI Language Models Write Good Doctor…

Generative AI should be able to write usable doctor's letters and thus potentially speed up medical documentation, according to a study by the University Medical Center Freiburg. Around 93% of...

Clanwilliam Brings Epic Care to the UK

Care homes looking to digitise their administration and care procedures have a new option with the launch of Epic Care in the UK. Epic Care is a modular, scalable system developed...

When Detecting Depression, the Eyes have…

It has been estimated that nearly 300 million people, or about 4% of the global population, are afflicted by some form of depression. But detecting it can be difficult, particularly...

West Yorkshire and Harrogate Hospitals S…

Clinicians working at five of the six trusts in the West Yorkshire Association of Acute Trusts (WYAAT) can access test results from across their pathology network, following a summer roll-out...

ChatGPT Shows Human-Level Assessment of …

As artificial intelligence advances, its uses and capabilities in real-world applications continue to reach new heights that may even surpass human expertise. In the field of radiology, where a correct...

HWL 2024 Brings Together a Record Number…

1 - 2 October 2024, Luxembourg. The second edition of Healthcare Week Luxembourg on 1 and 2 October 2024, organised by the Federation of Luxembourg Hospitals (FHL), in partnership with the...

When it comes to Emergency Care, ChatGPT…

If ChatGPT were cut loose in the Emergency Department, it might suggest unneeded x-rays and antibiotics for some patients and admit others who didn't require hospital treatment, a new study...