Tag Archives: SFI

Surprising Findings: Using Mobile Phones to Predict Population Displacement After Major Disasters

Rising concerns over the consequences of mass refugee flows during several crises in the late 1970′s is what prompted the United Nations (UN) to call for the establishment of early warning systems for the first time. “In 1978-79 for example, the United Nations and UNHCR were clearly overwhelmed by and unprepared for the mass influx of Indochinese refugees in South East Asia. The number of boat people washed onto the beaches there seriously challenged UNHCR’s capability to cope. One of the issues was the lack of advance information. The result was much human suffering, including many deaths. It took too long for emergency assistance by intergovernmental and non-governmental organizations to reach the sites” (Druke 2012 PDF).

Forty years later, my colleagues at Flowminder are using location data from mobile phones to nowcast and predict population displacement after major disasters. Focusing on the devastating 2010 Haiti earthquake, the team analyzed the movement of 1.9 million mobile users before and after the earthquake. Naturally, the Flowminder team expected that the mass exodus from Port-au-Prince would be rather challenging to predict. Surprisingly, however, the predictability of people’s movements remained high and even increased during the three-month period following the earthquake.

The team just released their findings in a peer-reviewed study entitled: “Predictability of population displacement after the 2010 Haiti earthquake” (PNAS 2012). As the analysis reveals, “the destinations of people who left the capital during the first three weeks after the earthquake was highly correlated with their mobility patterns during normal times, and specifically with the locations in which people had significant social bonds, as measured by where they spent Christmas and New Year holidays” (PNAS 2012).

For the people who left Port-au-Prince, the duration of their stay outside the city, as well as the time for their return, all followed a skewed, fat-tailed distribution. The findings suggest that population movements during disasters may be significantly more predictable than previously thought” (PNAS 2012). Intriguingly, the analysis also revealed the period of time that people in Port-au-Prince waited to leave the city (and then return) was “power-law distributed, both during normal days and after the earthquake, albeit with different exponents (PNAS 2012).” Clearly then, “[p]eople’s movements are highly influenced by their historic behavior and their social bonds, and this fact remained even after one of the most severe disasters in history” (PNAS 2012).

 

I wonder how this approach could be used in combination with crowdsourced satellite imagery analysis on the one hand and with Agent Based Models on the other. In terms of crowdsourcing, I have in mind the work carried out by the Standby Volunteer Task Force (SBTF) in partnership with UNHCR and Tomnod in Somalia last year. SBTF volunteers (“Mapsters”) tagged over a quarter million features that looked liked IDP shelters in under 120 hours, yielding a triangulated country of approximately 47,500 shelters.

In terms of Agent Based Models (ABMs), some colleagues and I  worked on “simulating population displacements following a crisis”  back in 2006 while at the Santa Fe Institute (SFI). We decided to use an Agent Based Model because the data on population movement was simply not within our reach. Moreover, we were particularly interested in modeling movements of ethnic populations after a political crisis and thus within the context of a politically charged environment.

So we included a preference for “safety in numbers” within the model. This parameter can easily be tweaked to reflect a preference for moving to locations that allow for the maintenance of social bonds as identified in the Flowminder study. The figure above lists all the parameters we used in our simple decision theoretic model.

The output below depicts the Agent Based Model in action. The multi-colored panels on the left depict the geographical location of ethnic groups at a certain period of time after the crisis escalates. The red panels on the right depict the underlying social networks and bonds that correspond to the geographic distribution just described. The main variable we played with was the size or magnitude of the sudden onset crisis to determine whether and how people might move differently around various ethnic enclaves. The study long with the results are available in this PDF.

In sum, it would be interesting to carry out Flowminder’s analysis in combination with crowdsourced satellite imagery analysis and live sensor data feeding into an Agent Base Model. Dissertation, anyone?

Analyzing Call Dynamics to Assess the Impact of Earthquakes

Earthquakes can cripple communication infrastructure and influence the number of voice calls relayed through cell phone towers. Data from cell phone traffic can thus be used as a proxy to infer the epicenter of an earthquake and possibly the needs of the disaster affected population. In this blog post, I summarize the findings from a recent study carried out by Microsoft Research and the Santa Fe Institute (SFI).

The study assesses the impact of the 5.9 magnitude earthquake near Lac Kivu in February 2008 on Rwandan call data to explore the possibility of inferring the epicenter and potential needs of affected communities. Cellular networks continually generate “Call Data Records (CDR) for billing and maintenance purposes” which can be used can be used to make inferences following a disaster. Since the geographic spread of cell phones and towers is not randomly distributed, the authors used methods to capture propagating uncertainties about their inferences from the data. This is important to prioritize the collection of new data.

The study is based on the following 3 assumptions:

1. Cell tower traffic deviates statistically from the normal patterns and trends in case of an unusual event.
2. Areas that suffer larger disruptions experience deviations in call volume that persist for a longer period of time.
3. Disruptions are overall inversely proportional to the distance from the center(s) of a catastrophe.

Based on these assumptions, the authors develop algorithms to detect earthquakes, predict their epicenter and infer opportunities for assistance. The results? Using call data to detect when in February 2008 the earthquake took place yields a highly accurate result. The same is true for predicting the epicenter. This means that call activity and cell phone towers can be used as a large-scale seismic system.

As for inferring hardest hit areas, the authors find that their “predicted model is far superior to the baseline and provides predictions that are significantly better for k = 3, 4 and 5″ where k represents the number of days post-earthquake. In sum, “the results highlight the promise of performing predictive analysis with existing telecommunications infrastructure.” The study is available on the Artificial Intelligence for Development (AI-D) website.

In the future, combining call traffic data with crowdsourced SMS data (see this study on Haiti text messages) could perhaps provide even more detailed information on near real-time impact and needs following a disaster. I’d be very interested to see this kind of study done on call/SMS data before, during and after a contested election or major armed conflict. Could patterns in call/SMS data in one country provide distinct early warning signatures for elections and conflict in other crises?