Facebook is using location data to help communities recover from natural disaster

Facebook is using location data to help communities recover from natural disaster

Courtsey: Facebook

Natural disasters not only cause billions of dollars damage to property each year, but unfortunately, they cost many people their lives. Hurricanes, earthquakes, tsunamis, tornadoes, fires, and floods are some examples of natural disasters. Most instances of natural disasters occur unexpectedly and catch people off guard. People are not prepared for a natural disaster to protect their homes and families. After the disaster, humanitarian organizations face difficulties in locating affected people, what resources are required, and who is safe, because the information itself is extremely challenging and often impossible to capture through conventional data collection methods in a timely manner.

However, technology has always come forward to rescue humans from the perils of nature (though human activities hold the major responsibility for these jeopardies!). Especially, smartphones and their apps are providing some unprecedented solutions to ease the human life.

In yet another philanthropic endeavor, Facebook has announced a Facebook Disaster Map initiative to address the critical gap in information when responding to natural disasters. And Facebook could be providing this information via Facebook App.

Location Data

When people use the Facebook app with Location Services enabled, their latitudes and longitudes are received at regular intervals. Location information is used while delivering a feature or content that is most relevant to people. It allows Facebook to send Safety Check notifications to those in regions affected by natural disasters.

The same geolocation data, when aggregated and de-identified, provides valuable information to humanitarian organizations after a natural disaster. Facebook aggregates geolocalized points to 360 square meter grid or local administrative boundaries. Once each metric is calculated (e.g., the number of people in administrative or pixel unit x during time period y), spatial smoothing is performed. For each spatial location, a weighted average of the value in the tile itself with the values in neighboring tiles is computed; tiles that are closer have a bigger contribution to the final result. This local averaging results in a map with a smoother, clearer signal, reducing noise due to random variation while preserving the key signal and further protecting privacy.

Disaster Maps

Using the data and aggregation techniques Facebook is able to generate following three unique and complementary datasets:

Location density maps

As mentioned above by aggregating geolocation data, Facebook is able to show a smoothed representation of how many people with location services enabled are using Facebook’s app in each administrative region or map grid for each time period.

Conversely, this data also has a limitation — it is not immediately obvious which values represent important deviations from normal. To tackle this, Facebook includes baseline counts — an approximation of how many people are in each administrative area averaged over the previous three weeks at the same time. Thus, the differences observed by matching on location and time are due to the disaster event and important to focus on.

Additional statistics is also given on this map to indicate whether the observed changes in density are statistically meaningful.

Movement maps

This dataset contains information about the number of people moving between tile pairs over a given time period. This is measured during baseline (movement between tile pairs averaged across the three weeks prior to the disaster) as well; so that it is clear how much more or fewer people are moving during the disaster period compared to usual. This helps in distinguishing disaster-related movements from people’s normal migration patterns.

Safety Check Maps

Some of the metrics provided by this map for each disaster derive from Facebook’s Safety Check product. Safety Check helps people connect with friends and family during a disaster. People are invited that might be affected by the crisis to check in safe. Once they have checked in, they can then invite others that might be affected. In this way, invitations to check in safe spread to people on Facebook who are likely affected by a disaster. For Safety Check Maps, the Safety Check data is aggregated and shared to show where people are indicating that they are safe.

The Privacy Issue

Nevertheless, sharing of such data is bound to raise some eyebrows. So, as a next step, Facebook also made clear that it would be teaming up with only trusted organizations that have the capacity to act on the data and respect the privacy standards. The announcement stated, “Starting with UNICEF, the International Federation of the Red Cross and Red Crescent Societies, and the World Food Programme. We are working with these organizations to establish formal processes for responsibly sharing the datasets with others. Over time, we intend to make it possible for additional organizations and governments to participate in this program. All applications will be reviewed carefully by people at Facebook, including those with local expertise.”

Also Read: How Facebook uses AI, machine learning & satellite imagery to locate unconnected people