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?
iRevolutions 