{"id":610040,"date":"2023-02-20T07:49:43","date_gmt":"2023-02-20T13:49:43","guid":{"rendered":"https:\/\/news.sellorbuyhomefast.com\/index.php\/2023\/02\/20\/how-ai-can-actually-be-helpful-in-disaster-response\/"},"modified":"2023-02-20T07:49:43","modified_gmt":"2023-02-20T13:49:43","slug":"how-ai-can-actually-be-helpful-in-disaster-response","status":"publish","type":"post","link":"https:\/\/newsycanuse.com\/index.php\/2023\/02\/20\/how-ai-can-actually-be-helpful-in-disaster-response\/","title":{"rendered":"How AI can actually be helpful in disaster response"},"content":{"rendered":"
\n

This article is from The Technocrat, MIT Technology Review’s weekly tech policy newsletter about power, politics, and Silicon Valley. To receive it in your inbox every Friday,\u00a0sign up here<\/a>.<\/em><\/p>\n

We often hear big (and unrealistic) promises about the potential of\u00a0AI to solve the world\u2019s ills<\/a>, and I was skeptical when I first learned that AI might be starting to aid disaster response, including following the\u00a0earthquake that has devastated Turkey and Syria.<\/p>\n<\/p><\/div>\n

\n

But one effort from the US Department of Defense does seem to be effective: xView2. Though it\u2019s still in its early phases of deployment, this visual computing project has already helped with disaster logistics and on the ground rescue missions in Turkey.<\/p>\n

An open-source project that was sponsored and developed by the Pentagon\u2019s\u00a0Defense Innovation Unit<\/a>\u00a0and Carnegie Mellon University’s Software Engineering Institute in 2019,\u00a0xView2<\/a>\u00a0has collaborated with many research partners, including Microsoft and the University of California, Berkeley. It uses machine-learning algorithms in conjunction with satellite imagery from other providers to identify building and infrastructure damage in the disaster area and categorize its severity much faster than is possible with current methods.<\/p>\n

Ritwik Gupta, the principal AI scientist at the Defense Innovation Unit and a researcher at Berkeley, tells me this means the program can directly help first responders and recovery experts on the ground quickly get an assessment that can aid in finding survivors and help coordinate reconstruction efforts over time.\u00a0<\/strong><\/p>\n

In this process, Gupta often works with big international organizations like the US National Guard, the United Nations, and the World Bank. Over the past five years, xView2 has been deployed by the California National Guard<\/a> and the Australian Geospatial-Intelligence Organisation in response to wildfires, and more recently during recovery efforts after flooding in Nepal<\/a>, where it helped identify damage created by subsequent landslides.\u00a0<\/p>\n

In Turkey, Gupta says xView2 has been used by at least two different ground teams of search and rescue personnel from the UN\u2019s International Search and Rescue Advisory Group<\/a> in Adiyaman, Turkey, which has been devastated by the earthquake and where residents have been frustrated by the delayed arrival of search and rescue<\/a>. xView2 has also been utilized elsewhere in the disaster zone, and was able to successfully help workers on the ground be \u201cable to find areas that were damaged that they were unaware of,\u201d he says, noting Turkey\u2019s Disaster and Emergency Management Presidency, the World Bank, the International Federation of the Red Cross, and the United Nations World Food Programme have all used the platform in response to the earthquake.<\/p>\n

\u201cIf we can save one life, that\u2019s a good use of the technology,\u201d Gupta tells me.<\/p>\n

How AI can help<\/strong><\/h3>\n

The algorithms employ a technique similar to object recognition, called \u201csemantic segmentation,\u201d which evaluates each individual pixel of an image and its relationship to adjacent pixels to draw conclusions.\u00a0<\/p>\n

Below, you can see snapshots of how this looks on the platform, with satellite images of the damage on the left and the model\u2019s assessment on the right\u2014the darker the red, the worse the wreckage. Atishay Abbhi, a disaster risk management specialist at the World Bank, tells me that this same degree of assessment would typically take weeks and now takes hours or minutes.\u00a0<\/p>\n<\/p><\/div>\n

\n
Marash, Turkey: Satellite imagery (left) from earth imaging company Planet Labs PBC and the output from xView2 (right) attributed to UC Berkeley, the Defense Innovation Unit, and Microsoft.<\/em><\/figcaption><\/figure>\n

This is an improvement over more traditional disaster assessment systems, in which rescue and emergency responders rely on eyewitness reports and calls to identify where help is needed quickly. In some more recent cases, fixed-wing aircrafts like drones have flown over disaster areas with cameras and sensors to provide data reviewed by humans, but this can still <\/strong>take days, if not longer. The typical response is further slowed by the fact that different responding organizations often have their own siloed data catalogues, making it challenging to create a standardized, shared picture of which areas need help. xView2 can create a shared map of the affected area in minutes, which helps organizations coordinate and prioritize responses\u2014saving time and lives.\u00a0<\/p>\n

The hurdles<\/strong><\/h3>\n

This technology, of course, is far from a cure-all for disaster response. There are several big challenges to xView2 that currently consume much of Gupta\u2019s research attention.\u00a0<\/p>\n

First and most important is how reliant the model is on satellite imagery, which delivers clear photos only during the day, when there is no cloud cover, and when a satellite is overhead. The first usable images out of Turkey didn\u2019t come until February 9, three days after the first quake. And there are far fewer satellite images taken in remote and less economically developed areas\u2014just across the border in Syria, for example. To address this, Gupta is researching new imaging techniques like synthetic aperture radar, which creates images using microwave pulses rather than light waves.\u00a0<\/p>\n

Second, while the xView2 model is up to 85 or 90% accurate in its precise evaluation of damage and severity, it also can\u2019t really spot damage on the sides of buildings, since satellite images have an aerial perspective.\u00a0<\/p>\n

Lastly, Gupta says getting on-the-ground organizations to use and trust an AI solution has been difficult. \u201cFirst responders are very traditional,\u201d he says. \u201cWhen you start telling them about this fancy AI model, which isn\u2019t even on the ground and it\u2019s looking at pixels from like 120 miles in space, they\u2019re not gonna trust it whatsoever.\u201d\u00a0<\/p>\n

What\u2019s next<\/strong><\/h3>\n

xView2 assists with multiple stages of disaster response, from immediately mapping out damaged areas to evaluating where safe temporary shelter sites could go to scoping longer-term reconstruction. Abbhi, for one, says he hopes xView2 \u201cwill be really important in our arsenal of damage assessment tools\u201d at the World Bank moving forward.\u00a0<\/p>\n

Since the code is open source<\/a> and the program is free, anyone could use it. And Gupta intends to keep it that way. \u201cWhen companies come in and start saying, We could commercialize this<\/em>, I hate that,\u201d he says. \u201cThis should be a public service that\u2019s operated for the good of everyone.\u201d Gupta is working on a web app so any user can run assessments; currently, organizations reach out to xView2 researchers for the analysis.\u00a0<\/p>\n<\/p><\/div>\n

\n

Rather than writing off or over-hyping the role that emerging technologies can play in big problems, Gupta says, researchers should focus on the types of AI that can make the biggest humanitarian impact. \u201cHow do we shift the focus of AI as a field to these immensely hard problems?\u201d he asks. \u201c[These are], in my opinion, much harder than\u2014for example\u2014generating new text or new images.\u201d<\/p>\n

What else I\u2019m reading<\/h3>\n

Teenage girls are not all right<\/a>. New research from the CDC<\/a> shows that mental health for high school girls has significantly worsened recently\u2014a crisis experts think has been intensified by social media and the pandemic.\u00a0<\/p>\n