The mission to create a searchable database of Earth's surface | Will Marshall

譯者: Lilian Chiu 審譯者: 易帆 余

Four years ago, here at TED,

四年前，在這個 TED 會場，

I announced Planet's Mission 1:

我宣佈了《星球任務一號》：

to launch a fleet of satellites

我們發射了一支衛星艦隊，

that would image the entire Earth, every day,

用來拍攝地球每天的影像，

and to democratize access to it.

並讓大眾能取得這些資訊。

The problem we were trying to solve was simple.

我們要解決的問題很簡單。

Satellite imagery you find online is old, typically years old,

你在網路上看到的衛星影像 是舊的，通常是幾年前的，

yet human activity was happening on days and weeks and months,

但人類的活動卻是每天、 每週、每月都在發生，

and you can't fix what you can't see.

你看不到，就無法改善。

We wanted to give people the tools to see that change and take action.

我們想要提供一些工具， 幫大家看到改變並採取行動。

The beautiful Blue Marble image, taken by the Apollo 17 astronauts in 1972

這張美麗的藍色彈珠照片是 1972 年 阿波羅 17 號的太空人所拍攝的，

had helped humanity become aware that we're on a fragile planet.

這張照片讓人類明白到， 我們居住的星球是很脆弱的。

And we wanted to take it to the next level,

我們還想要更上一層樓，

to give people the tools to take action, to take care of it.

提供工具，讓大家能 採取行動，關心地球。

Well, after many Apollo projects of our own,

在我們執行了許多阿波羅計畫、

launching the largest fleet of satellites in human history,

發射了人類史上 最大的一支衛星艦隊後，

we have reached our target.

我們終於達成了目標。

Today, Planet images the entire Earth, every single day.

現在，《星球任務》每天 都能為整個地球拍攝影像。

Mission accomplished.

任務完成。

(Applause)

（掌聲）

Thank you.

謝謝。

It's taken 21 rocket launches --

總共花了 21 次的火箭發射——

this animation makes it look really simple -- it was not.

這動畫使這任務看似簡單， 但其實不然。

And we now have over 200 satellites in orbit,

現在軌道上的衛星超過 200 個，

downlinking their data to 31 ground stations we built around the planet.

向我們建立在地面的 31 站下傳資料。

In total, we get 1.5 million 29-megapixel images of the Earth down each day.

我們每天總共下傳 150 萬張 29 百萬畫素的地球影像。

And on any one location of the Earth's surface,

在地球表面的任何一個地點，

we now have on average more than 500 images.

現在平均有超過 500 張影像。

A deep stack of data, documenting immense change.

非常大量的資料， 記錄著巨大的改變。

And lots of people are using this imagery.

而且有許多人正在使用這些影像。

Agricultural companies are using it to improve farmers' crop yields.

農業公司用它們來改善 農夫的作物產量。

Consumer-mapping companies are using it to improve the maps you find online.

消費者製圖公司用它們 來改善你在線上看到的地圖。

Governments are using it for border security

政府把它們用在邊境安全上，

or helping with disaster response after floods and fires and earthquakes.

或對洪水、火災、地震 提供災難應變的幫助。

還有很多非政府組織使用它們。

And lots of NGOs are using it.

So, for tracking and stopping deforestation.

比如，可以追蹤和阻止森林砍伐。

Or helping to find the refugees fleeing Myanmar.

或是協助找到逃離緬甸的難民。

Or to track all the activities in the ongoing crisis in Syria,

或是追蹤所有敘利亞 正在發生的危機行動，

holding all sides accountable.

記錄各方的責任。

And today, I'm pleased to announce Planet stories.

今天，我很高興能來發佈 星球實驗室的故事。

Anyone can go online to planet.com

大家都可以上網造訪 planet.com，

open an account and see all of our imagery online.

開一個帳戶，在線上 看我們所有的影像。

It's a bit like Google Earth, except it's up-to-date imagery,

它有點像是 Google Earth， 只差在它是最新的影像，

and you can see back through time.

且你還能回頭看過去的影像。

You can compare any two days

你可以比較任何兩個日期，

and see the dramatic changes that happen around our planet.

看看我們的星球上發生的巨大改變。

Or you can create a time lapse through the 500 images that we have

或是你也可以用我們的 500 張影像來做縮時影片，

and see that change dramatically over time.

看看隨著時間發生了 什麼巨大的改變。

And you can share these over social media.

你還可以把它們分享到社交媒體上。

It's pretty cool.

它相當酷。

(Applause)

（掌聲）

Thank you.

謝謝。

We initially created this tool for news journalists,

我們最初創造這項工具， 是為了新聞記者，

who wanted to get unbiased information about world events.

對於全球的事件， 他們想取得無偏見的資訊。

But now we've opened it up for anyone to use,

但現在我們已經開放給大家使用，

for nonprofit or personal uses.

可做非營利使用或個人使用。

And we hope it will give people the tools to find and see the changes on the planet

我們希望這項工具能協助大家 找到並發現地球上的改變，

and take action.

進而採取行動。

OK, so humanity now has this database of information about the planet,

好，所以人類現在有了 關於地球的資料庫，

有隨時間改變的資訊。

changing over time.

What's our next mission, what's Mission 2?

我們的下一個任務， 任務二號是什麼？

In short, it's space plus AI.

簡言之，是太空加上人工智慧。

What we're doing with artificial intelligence

我們使用人工智慧

is finding the objects in all the satellite images.

是要在所有這些 衛星影像中找到物體。

The same AI tools that are used to find cats in videos online

只要使用在線上影片中找出貓咪的 人工智慧一樣的工具，

can also be used to find information on our pictures.

也能被用來尋找我們照片中的資訊。

So, imagine if you can say, this is a ship, this is a tree,

想像一下，如果你能分辨， 這是一艘船，這是一棵樹，

this is a car, this is a road, this is a building, this is a truck.

這是一台汽車，這是一條道路， 這是一棟大樓，這是一台卡車。

And if you could do that for all of the millions of images

若對每天傳下來的數百萬張影像

coming down per day,

都能夠這麼做，

then you basically create a database

基本上你就能建立起一個資料庫，

of all the sizable objects on the planet, every day.

內有地球上每天 所有物體的資訊，相當可觀。

And that database is searchable.

且那個資料庫能用來搜尋。

So that's exactly what we're doing.

那就是我們正在做的事。

Here's a prototype, working on our API.

這是用我們的 API （應用程式界面）做的原型。

This is Beijing.

這是北京。

So, imagine if we wanted to count the planes in the airport.

想像一下，如果我們 想要知道機場有幾架飛機。

We select the airport,

我們選擇機場，

and it finds the planes in today's image,

它就會在今天的影像中找到飛機，

and finds the planes in the whole stack of images before it,

並找到在這之前 一大堆影像中的飛機，

and then outputs this graph of all the planes in Beijing airport over time.

接著輸出這張圖，上面是 各時間點北京機場中的飛機。

Of course, you could do this for all the airports around the world.

當然，你可以對地球上 所有的機場做這件事。

And let's look here in the port of Vancouver.

咱們來看看這裡，溫哥華的港口。

So, we would do the same, but this time we would look for vessels.

我們可以做同樣的事， 但這次是要找船隻。

So, we zoom in on Vancouver, we select the area,

我們將溫哥華放大， 選擇這個區域，

and we search for ships.

搜尋船隻。

And it outputs where all the ships are.

它會輸出所有船隻的位置。

Now, imagine how useful this would be to people in coast guards

想像一下，對於海上防衛隊， 這是多麼有用的資訊，

who are trying to track and stop illegal fishing.

他們的工作是要追蹤 和阻止非法捕漁。

See, legal fishing vessels

看，合法的捕漁船隻，

transmit their locations using AIS beacons.

會用 AIS 信標來傳送它們的位置。

But we frequently find ships that are not doing that.

但我們常常會發現 沒有傳送信標的船隻。

The pictures don't lie.

照片不會說謊。

And so, coast guards could use that

所以，海上防衛隊能用那資訊，

and go and find those illegal fishing vessels.

去找出非法的捕漁船隻。

And soon we'll add not just ships and planes

不只是船和飛機，之後我們很快就會把

but all the other objects,

其它物體加上去，

and we can output data feeds

我們可以把資料輸出來，

of those locations of all these objects over time

你可以針對地點、時間區段做輸出，

that can be integrated digitally from people's work flows.

這些資料就可以在大家的 工作流程中做數位整合。

In time, we could get more sophisticated browsers

到時候，我們會有更精密的瀏覽器，

that people pull in from different sources.

讓大家可以納入多重來源的資料。

But ultimately, I can imagine us abstracting out the imagery entirely

但最終，我可以想像 我們完全把影像抽取出來，

and just having a queryable interface to the Earth.

並且有一個能夠查詢地球的介面。

Imagine if we could just ask,

想像一下，若我們能問：

"Hey, how many houses are there in Pakistan?

「嘿，在巴基斯坦有多少間房子？

Give me a plot of that versus time."

把那資料搭配時間，畫張圖給我。」

"How many trees are there in the Amazon

「亞馬遜有多少棵樹？

and can you tell me the locations of the trees that have been felled

你能不能告訴我，從上週到這週之間

between this week and last week?"

哪些位置的樹木被砍伐了？」

Wouldn't that be great?

那樣不是很棒嗎？

Well, that's what we're trying to go towards,

那是我們在試圖達成的目標，

and we call it "Queryable Earth."

我們稱它為「可查詢的地球」。

So, Planet's Mission 1 was to image the whole planet every day

所以，《星球任務一號》 是要做到每天拍攝地球影像，

and make it accessible.

並讓這資訊能被大家取得。

Planet's Mission 2 is to index all the objects on the planet over time

《星球任務二號》是要將地球上 各時間點的所有物體做索引，

and make it queryable.

並供大家查詢。

Let me leave you with an analogy.

最後，我跟大家做個比喻。

Google indexed what's on the internet and made it searchable.

Google 將網路上的東西 做了索引，並供大家搜尋。

Well, we're indexing what's on the Earth and making it searchable.

我們則是將地球上的東西 做索引，並供大家搜尋。

Thank you very much.

非常謝謝各位。

(Applause)

（掌聲）