The world is watching closely as food shortages grip parts of Africa and the Middle East. As humanitarian groups respond to the crisis, they have to solve a major problem: how to track food security in areas that are simply too remote or too dangerous to access.
The Famine Early Warning Systems Network (FEWSNET) has come up with an innovative answer. The U.S.-funded organization is working with DigitalGlobe, a Colorado satellite company, to crowdsource analysis of satellite imagery of South Sudan.
The effort will rely on thousands of volunteers — normal people with no subject matter expertise — to scour satellite images looking for things like livestock herds, temporary dwellings and permanent dwellings. The group has selected an area of 18,000 square kilometers across five counties in South Sudan to analyze.
“The crowd can identify settlement imagery, they can identify roads, hospitals, airplanes, you name it. It allows us to tap into this network of folks around the world, not necessarily in country, but they are folks who are interested and compelled by whatever the campaign is,” said Rhiannan Price, senior manager of the Seeing a Better World Program at DigitalGlobe.
“Rather than clicking through your phone and passively taking in information, our users are actively engaging and putting information back out there that is really helpful for our partners.”
DigitalGlobe’s platform, known as Tomnod, has more than 2 million unique users. Other crowdsourcing observation campaigns using satellite imagery include the effects of a wildfire in South Africa and counting seals in Antarctica.
But the work is particularly valuable in South Sudan, where an estimated 100,000 people have been forced to flee their homes in the five-county area because of violence. Conflict-ridden South Sudan is the only place in the world where famine has been declared in the past six years.
“For humanitarians to cover that kind of ground, especially when it’s insecure, is just not a safe approach,” said Price. “Satellite imagery offers a really helpful tool when it comes to assessing and evaluating what’s happening on the ground, trying to find those folks so we can get resources and actually quantify the situation there.”
DigitalGlobe owns and operates a constellation of high-resolution satellites and has collected thousands of recent images of the area in question. In order to best track damage and displacement, they are comparing the images with ones from 2015, when they did a similar project.
Chris Hillbruner, deputy chief of party at FEWSNET, said his organization is trying several innovative approaches in different parts of the world to collect data. In Yemen and northeast Nigeria, it has assembled a network of local data collectors that relays information. It has also launched a pilot project using cellphones to collect wage and market data in Madagascar to determine when laborers are in low demand, signaling a bad year for harvests.
“We’re piloting a variety of tools and I think technology can help us, but I would also say that there are limitations,” Hillbruner said. “At the end of the day, we still get the best information when people are able to go into these areas and get on the ground to collect information about what is happening.”
But high-resolution satellite imagery, where each pixel in the photograph represents 30 centimeters on the ground, may be the next best thing to having a person on the ground.
To date, Tomnod’s team of volunteers has identified more than 180,000 objects of interest, including traditional dwellings known as tukuls and herds of livestock. This is invaluable information that tells humanitarian organizations where they need to send help.
“When you think of some of the drivers behind food insecurity, things like conflict or drought or flood, things that affect food supplies, or affect population migration, those are areas where remote sensing, satellite imagery, really excel in a way that other analyses simply can’t compete with,” Price said.