How AI Can Really Help in Disaster Response

How AI Can Really Help in Disaster Response

How AI Can Really Help in Disaster Response

>>> DOWNLOAD MP3 <<<

Marash, Turkey: Satellite imagery (left) from Earth-imaging company Planet Labs PBC and release of xView2 (right) credited to UC Berkeley, the Defense Innovation Unit, and Microsoft.

It is an improvement over more traditional disaster assessment systems, in which rescuers and emergency responders rely on eyewitness reports and calls to quickly identify where help is needed. . In some more recent cases, fixed-wing aircraft like drones have flown over disaster areas with cameras and sensors to provide data reviewed by humans, but this can stilltake days or even longer. Typical response is further slowed by the fact that different responding organizations often have their own siled data catalogs, making it difficult to create a standardized, shared picture of areas that need help. xView2 can create a shared map of the affected area in minutes, helping organizations coordinate and prioritize responses, saving time and lives.


The obstacles

This technology, of course, is far from a panacea for disaster response. There are several big challenges to xView2 that are currently consuming much of Gupta’s research attention.

The first and most important is the model’s reliance on satellite imagery, which provides clear photos only during the day, when there is no cloud cover, and when a satellite is overhead. The first usable images from Turkey only arrived on February 9, three days after the first quake. And there are far fewer satellite images taken in remote and less economically developed areas, just across the Syrian border, for example. To solve this problem, Gupta is investigating new imaging techniques like Synthetic Aperture Radar, which creates images using microwave pulses rather than light waves.

Secondly, while the xView2 model is up to 85 or 90% accurate in its precise assessment of damage and severity, it also can’t really spot damage on the sides of buildings because satellite images have perspective Aerial.

Finally, Gupta says it has been difficult to get organizations in the field to use and trust an AI solution. “First responders are very traditional,” he says. “When you start telling them about this sophisticated AI model, which isn’t even on the ground and is looking at pixels about 120 miles out in space, they won’t trust it anymore.”

And after

xView2 helps at multiple stages of disaster response, from immediate mapping of damaged areas to assessing safe temporary shelter sites to determine longer-term reconstruction. Abbhi, for his part, says he hopes xView2 “will be really important in our arsenal of damage assessment tools” at the World Bank in the future.

As the code is open source and the program is free, anyone can use it. And Gupta intends to keep it that way. “When companies come in and start saying, We could market that, I hate it,” he says. “It should be a public service that works for the good of all.” Gupta is working on a web application so that any user can run assessments; currently, organizations are contacting xView2 researchers for analysis.


Do you find AfroNaija useful? Click here to give us five stars rating!

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button