论AI如何助力灾难响应

今年2月以来，土耳其地震频发，继2月6日7.7级地震后，当地时间20日晚（北京时间21日凌晨），土耳其再次接连发生两次6.4级和5.8级地震。据国际投行摩根大通公司2月16日报告分析，此次强震给土耳其造成的经济损失可能高达250亿美元。

近日，麻省理工科技评论发表题为《论AI如何助力灾难响应》文章，指出土耳其和叙利亚人道主义团队正在使用机器学习来快速确定地震破坏范围并制定救援计划。

How AI can actually be helpful in disaster response

论AI如何助力灾难响应

By Tate Ryan-Mosleyarchive

作者｜ Tate Ryan-Mosleyarchive

编译｜数乾坤（数据观）

Humanitarian teams in Turkey and Syria are using machine learning to quickly scope out earthquake damage and strategize rescue efforts

土耳其和叙利亚人道主义团队正在使用机器学习来快速确定地震破坏范围并制定救援工作计划。

Islahiye, Turkey - Satellite imagery (left) and the output from xView2 (right)

MAXAR TECHNOLOGIES (LEFT); UC BERKELEY/DEFENSE INNOVATION UNIT/MICROSOFT (RIGHT)

土耳其东南部小镇伊斯拉希耶 - 卫星图像（左）和 xView2 的输出（右）

麦克萨科技（左）；加州大学伯克利分校/国防创新部门/微软（右）

We often hear big (and unrealistic) promises about the potential of AI to solve the world’s ills, and I was skeptical when I first learned that AI might be starting to aid disaster response, including following the earthquake that has devastated Turkey and Syria.

AI常常被赋予一些华而不实的承诺，比如解决世界难题。首次了解到AI或被用于此次土耳其和叙利亚地震救灾时，我深表怀疑。

But one effort from the US Department of Defense does seem to be effective: xView2. Though it’s 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.

然而，美国国防部在xView2上的努力成果似乎印证了AI的有效性。虽然xView2仍在部署早期，但这个可视化计算项目已经在土耳其的灾难后勤和地面救援任务中派上用场。

An open-source project that was sponsored and developed by the Pentagon’s Defense Innovation Unit and Carnegie Mellon University's Software Engineering Institute in 2019, xView2 has 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.

xView2是一个由美国五角大楼国防创新部门和卡内基梅隆大学软件工程研究所于2019年 牵头和开发的开源项目，研究合作伙伴包括微软和加州大学伯克利分校等机构。它使用机器学习算法，结合其他供应商提供的卫星图像来识别灾区建筑和基础设施损坏情况，并对其损坏程度进行分类，比目前已知的其他方法要快得多。

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.

国防创新部门的首席AI科学家兼伯克利研究员Ritwik Gupta透露，这意味着该计划可以直接帮助现场的救援人员和恢复专家快速获得评估，从而帮助寻找幸存者并帮助协调灾后重建工作。

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 and the Australian Geospatial-Intelligence Organisation in response to wildfires, and more recently during recovery efforts after flooding in Nepal, where it helped identify damage created by subsequent landslides.

在这个过程中，Gupta经常与美国国民警卫队、联合国和世界银行等大型国际组织合作。在过去五年时间里，xView2已经被加利福尼亚国民警卫队和澳大利亚地理空间情报组织部署使用，以应对野火。最近，在尼泊尔洪水灾后工作中，它识别到紧随其后的山体滑坡所造成的破坏。

In Turkey, Gupta says xView2 has been used by at least two different ground teams of search and rescue personnel from the UN’s International Search and Rescue Advisory Group in Adiyaman, Turkey, which has been devastated by the earthquake and where residents have been frustrated by the delayed arrival of search and rescue. xView2 has also been utilized elsewhere in the disaster zone, and was able to successfully help workers on the ground be “able to find areas that were damaged that they were unaware of,” he says, noting Turkey’s 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.

Gupta表示，在土耳其的地震救援中，xView2 至少被两个不同的地面搜救队使用，这些地面搜救队来自土耳其阿德亚曼的联合国国际搜救小组。该地区已经被地震摧毁，居民因搜救人员延迟到达而感到沮丧。xView2在灾区的其他地方也得到了应用，并且能够成功帮助当地的工作人员搜寻到他们不知道的受损区域。土耳其的灾害和应急管理主席、世界银行、红十字国际联合会和联合国世界粮食计划署都在应对地震时使用了该平台。

“If we can save one life, that’s a good use of the technology,” Gupta tells me.

“如果我们能挽救一条生命，那这项技术就是用在点子上了”，Gupta说。

How AI can help

人工智能怎么发力？

The algorithms employ a technique similar to object recognition, called “semantic segmentation,” which evaluates each inpidual pixel of an image and its relationship to adjacent pixels to draw conclusions.

这些算法采用了一种类似于物体识别的技术，称为 "语义分割"，它评估了每个图像的单独像素以及与相邻像素的关系，从而得出结论。

Below, you can see snapshots of how this looks on the platform, with satellite images of the damage on the left and the model’s assessment on the right—the 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.

下面，你可以看到xView2 平台上的快照，左边是灾难破坏的卫星图像，右边是系统模型的评估——红色越深，残骸就越严重。世界银行的灾害风险管理专家Atishay Abbhi表示，这种程度的评估放在以前，通常需要几周时间，而现在有了xView2只需要几小时或几分钟。

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.

图为地震后的土耳其马拉什：来自地球成像公司 Planet Labs PBC 的卫星图像（左）和来自加州大学伯克利分校、国防创新部门和微软的 xView2 输出（右）。

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 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—saving time and lives.

这是对传统灾害评估系统的转型升级，在这个系统中，救援和应急响应人员依靠目击者的报告和电话来迅速确定哪里需要帮助。在最近的一些案例中，像无人机这样的固定翼飞机带着摄像机和传感器在灾区上空飞行，提供由人类审查的数据，但这仍然需要几天时间，甚至更久。由于不同的救灾组织往往有自己的独立数据目录，使得创建一个标准化的、可共享的关待救援地区图片变得很有挑战性，这有助于组织协调响应并确定响应的优先级，从而节省时间挽救更多生命。

The hurdles

阻碍

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’s research attention.

当然，这项技术远非灾难响应的灵丹妙药。目前，xView2 面临着几项重大挑战，这些挑战消耗了Gupta的大部分研究注意力。

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’t 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—just 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.

首先，最重要的是该模型对卫星图像的依赖程度，卫星图像只在白天没有云层和卫星覆盖的时候提供清晰的照片。土耳其第一批可用的图像直到2月9日才出现，即第一次地震发生后三天。而且，在偏远和经济欠发达地区拍摄的卫星图像要少得多——例如，叙利亚边境。为了解决这个问题，Gupta正在研究新的成像技术，如合成孔径雷达，它使用微波脉冲而非光波来创建图像。

Second, while the xView2 model is up to 85 or 90% accurate in its precise evaluation of damage and severity, it also can’t really spot damage on the sides of buildings, since satellite images have an aerial perspective.

其次，虽然 xView2 模型在精确评估损坏和严重程度方面的准确率高达 85% 或 90%，但它也无法真正发现建筑物侧面的损坏程度，因为卫星图像具有航空视角。

Lastly, Gupta says getting on-the-ground organizations to use and trust an AI solution has been difficult. “First responders are very traditional,” he says. “When you start telling them about this fancy AI model, which isn’t even on the ground and it’s looking at pixels from like 120 miles in space, they’re not gonna trust it whatsoever.”

Gupta表示，让救援实地组织使用和信任AI解决方案一直很困难。“救援人员非常传统，”他说。“当你告诉他们这个奇特的 AI 模型甚至不在地面上，而是从 120 英里的太空中来观察地面像素，他们无论如何都不会相信它。”

What’s next

路在何方

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 “will be really important in our arsenal of damage assessment tools” at the World Bank moving forward.

xView2可以协助多个阶段的救灾工作，从立即绘制受损地区的地图到评估安全的临时庇护所的位置，再到确定长期的灾后重建范围。Abbhi表示，他希望xView2在损害评估工具库中发挥重要作用，引领世界银行向前发展。

Since the code is open source and the program is free, anyone could use it. And Gupta intends to keep it that way. “When companies come in and start saying, We could commercialize this, I hate that,” he says. “This should be a public service that’s operated for the good of everyone.” Gupta is working on a web app so any user can run assessments; currently, organizations reach out to xView2 researchers for the analysis.

由于代码是开源的，程序是免费的，任何人都可以使用它，而且Gupta打算保持这种方式。他说：“当公司进来并开始说，我们可以把这个商业化，我讨厌这样。 xView2应该是一项公共服务，为了每个人的利益而运作。”目前，Gupta正在开发一个网络应用，这样任何用户都可以运行评估功能，而各组织也在向xView2的研究人员提供分析服务。

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. “How do we shift the focus of AI as a field to these immensely hard problems?” he asks. “[These are], in my opinion, much harder than—for example—generating new text or new images.”

Gupta认为，研究人员不应将新兴技术在大问题上发挥的作用一笔勾销或过度夸大，而应将重点放在能够产生最大人道主义影响的人工智能应用上。那么，如何将人工智能的重点作为一个领域转移到这些世界级难题上呢？“在我看来，这些比生成新文本或新图像要难得多。”