今年2月以來，土耳其地震頻發(fā)，繼2月6日7.7級地震后，當?shù)貢r間20日晚（北京時間21日凌晨），土耳其再次接連發(fā)生兩次6.4級和5.8級地震。據(jù)國際投行摩根大通公司2月16日報告分析，此次強震給土耳其造成的經(jīng)濟損失可能高達250億美元。

?

近日，麻省理工科技評論發(fā)表題為《論AI如何助力災難響應》文章，指出土耳其和敘利亞人道主義團隊正在使用機器學習來快速確定地震破壞范圍并制定救援計劃。

?

How AI can actually be helpful in disaster response

論AI如何助力災難響應

By Tate Ryan-Mosleyarchive

作者｜?Tate Ryan-Mosleyarchive

編譯｜數(shù)乾坤（數(shù)據(jù)觀）

?

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

土耳其和敘利亞人道主義團隊正在使用機器學習來快速確定地震破壞范圍并制定救援工作計劃。

?

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

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

土耳其東南部小鎮(zhèn)伊斯拉希耶 - 衛(wèi)星圖像（左）和 xView2 的輸出（右）

麥克薩科技（左）；加州大學伯克利分校/國防創(chuàng)新部門/微軟（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常常被賦予一些華而不實的承諾，比如解決世界難題。首次了解到AI或被用于此次土耳其和敘利亞地震救災時，我深表懷疑。

?

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，美國國防部在xView2上的努力成果似乎印證了AI的有效性。雖然xView2仍在部署早期，但這個可視化計算項目已經(jīng)在土耳其的災難后勤和地面救援任務中派上用場。

?

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是一個由美國五角大樓國防創(chuàng)新部門和卡內(nèi)基梅隆大學軟件工程研究所于2019年 牽頭和開發(fā)的開源項目，研究合作伙伴包括微軟和加州大學伯克利分校等機構(gòu)。它使用機器學習算法，結(jié)合其他供應商提供的衛(wèi)星圖像來識別災區(qū)建筑和基礎設施損壞情況，并對其損壞程度進行分類，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.

國防創(chuàng)新部門的首席AI科學家兼伯克利研究員Ritwik Gupta透露，這意味著該計劃可以直接幫助現(xiàn)場的救援人員和恢復專家快速獲得評估，從而幫助尋找幸存者并幫助協(xié)調(diào)災后重建工作。

?

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.

在這個過程中，Gupta經(jīng)常與美國國民警衛(wèi)隊、聯(lián)合國和世界銀行等大型國際組織合作。在過去五年時間里，xView2已經(jīng)被加利福尼亞國民警衛(wèi)隊和澳大利亞地理空間情報組織部署使用，以應對野火。最近，在尼泊爾洪水災后工作中，它識別到緊隨其后的山體滑坡所造成的破壞。

?

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 至少被兩個不同的地面搜救隊使用，這些地面搜救隊來自土耳其阿德亞曼的聯(lián)合國國際搜救小組。該地區(qū)已經(jīng)被地震摧毀，居民因搜救人員延遲到達而感到沮喪。xView2在災區(qū)的其他地方也得到了應用，并且能夠成功幫助當?shù)氐墓ぷ魅藛T搜尋到他們不知道的受損區(qū)域。土耳其的災害和應急管理主席、世界銀行、紅十字國際聯(lián)合會和聯(lián)合國世界糧食計劃署都在應對地震時使用了該平臺。

?

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

“如果我們能挽救一條生命，那這項技術就是用在點子上了”，Gupta說。

?

How AI can help

人工智能怎么發(fā)力？

?

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

這些算法采用了一種類似于物體識別的技術，稱為 "語義分割"，它評估了每個圖像的單獨像素以及與相鄰像素的關系，從而得出結(jié)論。

?

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，您可以看到它在平臺上的樣子的快照，左邊是損壞的衛(wèi)星圖像，右邊是模型的評估——紅色越深，殘骸越嚴重。世界銀行災害風險管理專家 Atishay Abbhi 告訴我，同樣程度的評估通常需要數(shù)周時間，而現(xiàn)在只需數(shù)小時或數(shù)分鐘。

?

下面，你可以看到xView2 平臺上的快照，左邊是災難破壞的衛(wèi)星圖像，右邊是系統(tǒng)模型的評估——紅色越深，殘骸就越嚴重。世界銀行的災害風險管理專家Atishay Abbhi表示，這種程度的評估放在以前，通常需要幾周時間，而現(xiàn)在有了xView2只需要幾小時或幾分鐘。

?

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.

圖為地震后的土耳其馬拉什：來自地球成像公司 Planet Labs PBC 的衛(wèi)星圖像（左）和來自加州大學伯克利分校、國防創(chuàng)新部門和微軟的 xView2 輸出（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.

這是對傳統(tǒng)災害評估系統(tǒng)的轉(zhuǎn)型升級，在這個系統(tǒng)中，救援和應急響應人員依靠目擊者的報告和電話來迅速確定哪里需要幫助。在最近的一些案例中，像無人機這樣的固定翼飛機帶著攝像機和傳感器在災區(qū)上空飛行，提供由人類審查的數(shù)據(jù)，但這仍然需要幾天時間，甚至更久。由于不同的救災組織往往有自己的獨立數(shù)據(jù)目錄，使得創(chuàng)建一個標準化的、可共享的關待救援地區(qū)圖片變得很有挑戰(zhàn)性，這有助于組織協(xié)調(diào)響應并確定響應的優(yōu)先級，從而節(jié)省時間挽救更多生命。

?

?

The hurdles

阻礙

?

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.

當然，這項技術遠非災難響應的靈丹妙藥。目前，xView2 面臨著幾項重大挑戰(zhàn)，這些挑戰(zhàn)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，最重要的是該模型對衛(wèi)星圖像的依賴程度，衛(wèi)星圖像只在白天沒有云層和衛(wèi)星覆蓋的時候提供清晰的照片。土耳其第一批可用的圖像直到2月9日才出現(xiàn)，即第一次地震發(fā)生后三天。而且，在偏遠和經(jīng)濟欠發(fā)達地區(qū)拍攝的衛(wèi)星圖像要少得多——例如，敘利亞邊境。為了解決這個問題，Gupta正在研究新的成像技術，如合成孔徑雷達，它使用微波脈沖而非光波來創(chuàng)建圖像。

?

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，雖然 xView2 模型在精確評估損壞和嚴重程度方面的準確率高達 85% 或 90%，但它也無法真正發(fā)現(xiàn)建筑物側(cè)面的損壞程度，因為衛(wèi)星圖像具有航空視角。

?

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，讓救援實地組織使用和信任AI解決方案一直很困難。“救援人員非常傳統(tǒng)，”他說。“當你告訴他們這個奇特的 AI 模型甚至不在地面上，而是從 120 英里的太空中來觀察地面像素，他們無論如何都不會相信它?！?

?

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可以協(xié)助多個階段的救災工作，從立即繪制受損地區(qū)的地圖到評估安全的臨時庇護所的位置，再到確定長期的災后重建范圍。Abbhi表示，他希望xView2在損害評估工具庫中發(fā)揮重要作用，引領世界銀行向前發(fā)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.

由于代碼是開源的，程序是免費的，任何人都可以使用它，而且Gupta打算保持這種方式。他說：“當公司進來并開始說，我們可以把這個商業(yè)化，我討厭這樣。 xView2應該是一項公共服務，為了每個人的利益而運作?！蹦壳埃珿upta正在開發(fā)一個網(wǎng)絡應用，這樣任何用戶都可以運行評估功能，而各組織也在向xView2的研究人員提供分析服務。

?

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認為，研究人員不應將新興技術在大問題上發(fā)揮的作用一筆勾銷或過度夸大，而應將重點放在能夠產(chǎn)生最大人道主義影響的人工智能應用上。那么，如何將人工智能的重點作為一個領域轉(zhuǎn)移到這些世界級難題上呢？“在我看來，這些比生成新文本或新圖像要難得多?！?/p>