PlanetSense: Stepping in when disaster strikes
As Hurricane Dorian raged through the Bahamas, researchers at Oak Ridge National Laboratory worked around the clock to aid recovery efforts for one of the Caribbean's worst storms ever.
Dorian made landfall on the island nation Sept. 1, 2019, with winds that topped speeds of 185 mph, leaving communities devastated in its wake and relief agencies around the globe scrambling to assist survivors. Gautam Thakur, a research scientist in ORNL's Geospatial Science and Human Security Division, and his team helped direct that relief, churning out geographic data that guided decisions on everything from where to open emergency shelters to how to staff first-aid centers.
"One of the things that makes me proud to come in here every day is knowing the impact we can make by saving lives in this way," Thakur said. "We're doing things that matter for national security and global peace."
Thakur, whose research focuses on the intersection of people, places, and computing, leads work on the PlanetSense program, a digital dragnet and real-time mapping platform that draws on volunteered geographic information (such as public posts on Facebook and Twitter about what's happening in a particular place), breaking news, the internet of things, and other online chatter to track disasters and other major events worldwide as they happen. The program got off the ground about three years ago, part of the Geoinformatics Engineering Group.
"Any time something like this happens, there's a large trail of location-based data out there that people like you and me put out from moment to moment," Thakur said. "People are sharing pictures and videos on public-domain websites as events happen in real time. They're implicitly volunteering critical geographic information: 'I'm here in the Grand Bahamas, and the hospital where I work is damaged.' But there were no tools to real-time process all this data. We know we have the required computational competency here at ORNL that can process it accurately and at high speed."
Thakur's team combined the details harvested by PlanetSense with satellite imagery of the hurricane and laid that picture over flood maps of the islands to pinpoint Dorian's impact. The team then identified the places hardest hit, from a sky-level view to individual buildings, sewer systems, and power grids.
"If you don't know the impact, you can't mobilize the people," Thakur said. "If a school is in the hurricane's path, it's not likely to make a good emergency shelter. We can compare pictures of the school before and after the hurricane. We can identify where the infrastructure is and whether it's likely to be damaged or safe. We can help determine the locations of shelters and help pinpoint where more people will be required."
Relying solely on confirmed reports from witnesses on the ground can take weeks or months to paint a full picture of a storm's toll. That kind of timeline wasn't an option when Dorian hit.
"People put their lives on this data," Thakur said. "No one has six months to evaluate it. The first responders have to go now."
Researchers used a ground-up approach to design what Thakur describes as a scalable, location-based intelligence-gathering platform. An early PlanetSense storm-chasing effort, tracking Hurricane Irma in 2017, took a turnaround time of about a week. By the time Dorian hit two years later, the team shrank that timetable to a 24- to 48-hour window, with the majority of the results still eyeballed by analysts.
"One of the challenges is to know how to trust this information," Thakur said. "Is there a second line of evidence? We always have to verify."
PlanetSense detects sudden bursts of online activity as they happen - photos, video, text - that can signal such events as hurricanes, wildfires or other events related to national security. The system can pick up keywords - fire, storm, flood - and spot clusters of similar posts from the same area.
"When we get that kind of information during one of these events, the system starts to spike," Thakur said. "The whisper becomes a roar."
Thakur and a team of 14 data analysts, geographers and others then start putting the pieces together to get a picture of what's happening where.
"I'm a computer scientist, and I tend to think in very binary, zero-and-one terms," Thakur said. "The human-dynamics geographers see the fuzziness between the zeroes and ones. We need both. The whole approach increases autonomy, observability, and confidence toward the decision-making process to advance the science of national security."
The inspiration for PlanetSense came around 2014, when Thakur helped collect volunteered geographic information and other social-media data for a project that mapped relative occupancy at the University of Tennessee's Neyland Stadium on football game days before and after kickoff.
"That's how it evolved over time," he said. "We wanted to know: Can we make this idea bigger, possibly covering the entire planet and sensing it every second? What really excited me to pursue this is primarily for the humanitarian impact. Even if I can make just a small difference with this work, it's so impactful. This is the kind of computing you can use for the benefit of humankind."
Some of his grad-school classmates, former colleagues, and other friends hold jobs at the online economy's biggest software companies. When they ask what he's doing at ORNL, he smiles.
"I tell them: 'I'm saving lives!' " he said. "You can't put a price on that."
UT-Battelle manages ORNL for the Department of Energy's Office of Science, the single largest supporter of basic research in the physical sciences in the United States. The Office of Science is working to address some of the most pressing challenges of our time. For more information, please visit energy.gov/science.