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

103,334 views ・ 2018-08-13

TED


請雙擊下方英文字幕播放視頻。

譯者: Lilian Chiu 審譯者: 易帆 余
00:12
Four years ago, here at TED,
0
12761
2215
四年前,在這個 TED 會場,
00:15
I announced Planet's Mission 1:
1
15000
2336
我宣佈了《星球任務一號》:
00:17
to launch a fleet of satellites
2
17360
1856
我們發射了一支衛星艦隊,
00:19
that would image the entire Earth, every day,
3
19240
2280
用來拍攝地球每天的影像,
00:22
and to democratize access to it.
4
22560
1640
並讓大眾能取得這些資訊。
00:25
The problem we were trying to solve was simple.
5
25520
2216
我們要解決的問題很簡單。
00:27
Satellite imagery you find online is old, typically years old,
6
27760
3096
你在網路上看到的衛星影像 是舊的,通常是幾年前的,
00:30
yet human activity was happening on days and weeks and months,
7
30880
3936
但人類的活動卻是每天、 每週、每月都在發生,
00:34
and you can't fix what you can't see.
8
34840
2256
你看不到,就無法改善。
00:37
We wanted to give people the tools to see that change and take action.
9
37120
3776
我們想要提供一些工具, 幫大家看到改變並採取行動。
00:40
The beautiful Blue Marble image, taken by the Apollo 17 astronauts in 1972
10
40920
4936
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,
00:45
had helped humanity become aware that we're on a fragile planet.
11
45880
3280
這張照片讓人類明白到, 我們居住的星球是很脆弱的。
00:49
And we wanted to take it to the next level,
12
49600
2056
我們還想要更上一層樓,
00:51
to give people the tools to take action, to take care of it.
13
51680
3456
提供工具,讓大家能 採取行動,關心地球。
00:55
Well, after many Apollo projects of our own,
14
55160
4056
在我們執行了許多阿波羅計畫、
00:59
launching the largest fleet of satellites in human history,
15
59240
2960
發射了人類史上 最大的一支衛星艦隊後,
01:03
we have reached our target.
16
63600
1520
我們終於達成了目標。
01:06
Today, Planet images the entire Earth, every single day.
17
66080
3656
現在,《星球任務》每天 都能為整個地球拍攝影像。
01:09
Mission accomplished.
18
69760
1216
任務完成。
01:11
(Applause)
19
71000
2536
(掌聲)
01:13
Thank you.
20
73560
1200
謝謝。
01:15
It's taken 21 rocket launches --
21
75600
3976
總共花了 21 次的火箭發射——
01:19
this animation makes it look really simple -- it was not.
22
79600
4160
這動畫使這任務看似簡單, 但其實不然。
01:25
And we now have over 200 satellites in orbit,
23
85040
3456
現在軌道上的衛星超過 200 個,
01:28
downlinking their data to 31 ground stations we built around the planet.
24
88520
3936
向我們建立在地面的 31 站下傳資料。
01:32
In total, we get 1.5 million 29-megapixel images of the Earth down each day.
25
92480
6296
我們每天總共下傳 150 萬張 29 百萬畫素的地球影像。
01:38
And on any one location of the Earth's surface,
26
98800
2416
在地球表面的任何一個地點,
01:41
we now have on average more than 500 images.
27
101240
3496
現在平均有超過 500 張影像。
01:44
A deep stack of data, documenting immense change.
28
104760
3880
非常大量的資料, 記錄著巨大的改變。
01:49
And lots of people are using this imagery.
29
109320
2536
而且有許多人正在使用這些影像。
01:51
Agricultural companies are using it to improve farmers' crop yields.
30
111880
5136
農業公司用它們來改善 農夫的作物產量。
01:57
Consumer-mapping companies are using it to improve the maps you find online.
31
117040
4176
消費者製圖公司用它們 來改善你在線上看到的地圖。
02:01
Governments are using it for border security
32
121240
2096
政府把它們用在邊境安全上,
02:03
or helping with disaster response after floods and fires and earthquakes.
33
123360
3680
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。
02:08
And lots of NGOs are using it.
34
128320
1536
02:09
So, for tracking and stopping deforestation.
35
129880
3416
比如,可以追蹤和阻止森林砍伐。
02:13
Or helping to find the refugees fleeing Myanmar.
36
133320
3536
或是協助找到逃離緬甸的難民。
02:16
Or to track all the activities in the ongoing crisis in Syria,
37
136880
4376
或是追蹤所有敘利亞 正在發生的危機行動,
02:21
holding all sides accountable.
38
141280
1680
記錄各方的責任。
02:24
And today, I'm pleased to announce Planet stories.
39
144640
3456
今天,我很高興能來發佈 星球實驗室的故事。
02:28
Anyone can go online to planet.com
40
148120
2296
大家都可以上網造訪 planet.com,
02:30
open an account and see all of our imagery online.
41
150440
3240
開一個帳戶,在線上 看我們所有的影像。
02:34
It's a bit like Google Earth, except it's up-to-date imagery,
42
154480
3096
它有點像是 Google Earth, 只差在它是最新的影像,
02:37
and you can see back through time.
43
157600
2680
且你還能回頭看過去的影像。
02:41
You can compare any two days
44
161040
1696
你可以比較任何兩個日期,
02:42
and see the dramatic changes that happen around our planet.
45
162760
2880
看看我們的星球上發生的巨大改變。
02:46
Or you can create a time lapse through the 500 images that we have
46
166560
3400
或是你也可以用我們的 500 張影像來做縮時影片,
02:50
and see that change dramatically over time.
47
170600
2560
看看隨著時間發生了 什麼巨大的改變。
02:54
And you can share these over social media.
48
174000
2720
你還可以把它們分享到社交媒體上。
02:57
It's pretty cool.
49
177520
1216
它相當酷。
02:58
(Applause)
50
178760
1216
(掌聲)
03:00
Thank you.
51
180000
1200
謝謝。
03:02
We initially created this tool for news journalists,
52
182440
2456
我們最初創造這項工具, 是為了新聞記者,
03:04
who wanted to get unbiased information about world events.
53
184920
2736
對於全球的事件, 他們想取得無偏見的資訊。
03:07
But now we've opened it up for anyone to use,
54
187680
2216
但現在我們已經開放給大家使用,
03:09
for nonprofit or personal uses.
55
189920
2000
可做非營利使用或個人使用。
03:12
And we hope it will give people the tools to find and see the changes on the planet
56
192600
4416
我們希望這項工具能協助大家 找到並發現地球上的改變,
03:17
and take action.
57
197040
1200
進而採取行動。
03:18
OK, so humanity now has this database of information about the planet,
58
198920
4256
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。
03:23
changing over time.
59
203200
1216
03:24
What's our next mission, what's Mission 2?
60
204440
2056
我們的下一個任務, 任務二號是什麼?
03:26
In short, it's space plus AI.
61
206520
2440
簡言之,是太空加上人工智慧。
03:29
What we're doing with artificial intelligence
62
209720
2176
我們使用人工智慧
03:31
is finding the objects in all the satellite images.
63
211920
3096
是要在所有這些 衛星影像中找到物體。
03:35
The same AI tools that are used to find cats in videos online
64
215040
4536
只要使用在線上影片中找出貓咪的 人工智慧一樣的工具,
03:39
can also be used to find information on our pictures.
65
219600
3896
也能被用來尋找我們照片中的資訊。
03:43
So, imagine if you can say, this is a ship, this is a tree,
66
223520
3336
想像一下,如果你能分辨, 這是一艘船,這是一棵樹,
03:46
this is a car, this is a road, this is a building, this is a truck.
67
226880
4376
這是一台汽車,這是一條道路, 這是一棟大樓,這是一台卡車。
03:51
And if you could do that for all of the millions of images
68
231280
2736
若對每天傳下來的數百萬張影像
03:54
coming down per day,
69
234040
1256
都能夠這麼做,
03:55
then you basically create a database
70
235320
1736
基本上你就能建立起一個資料庫,
03:57
of all the sizable objects on the planet, every day.
71
237080
2656
內有地球上每天 所有物體的資訊,相當可觀。
03:59
And that database is searchable.
72
239760
1560
且那個資料庫能用來搜尋。
04:02
So that's exactly what we're doing.
73
242520
2096
那就是我們正在做的事。
04:04
Here's a prototype, working on our API.
74
244640
2256
這是用我們的 API (應用程式界面)做的原型。
04:06
This is Beijing.
75
246920
1456
這是北京。
04:08
So, imagine if we wanted to count the planes in the airport.
76
248400
2856
想像一下,如果我們 想要知道機場有幾架飛機。
04:11
We select the airport,
77
251280
1856
我們選擇機場,
04:13
and it finds the planes in today's image,
78
253160
2376
它就會在今天的影像中找到飛機,
04:15
and finds the planes in the whole stack of images before it,
79
255560
3256
並找到在這之前 一大堆影像中的飛機,
04:18
and then outputs this graph of all the planes in Beijing airport over time.
80
258840
4896
接著輸出這張圖,上面是 各時間點北京機場中的飛機。
04:23
Of course, you could do this for all the airports around the world.
81
263760
3576
當然,你可以對地球上 所有的機場做這件事。
04:27
And let's look here in the port of Vancouver.
82
267360
2936
咱們來看看這裡,溫哥華的港口。
04:30
So, we would do the same, but this time we would look for vessels.
83
270320
3536
我們可以做同樣的事, 但這次是要找船隻。
04:33
So, we zoom in on Vancouver, we select the area,
84
273880
4136
我們將溫哥華放大, 選擇這個區域,
04:38
and we search for ships.
85
278040
2056
搜尋船隻。
04:40
And it outputs where all the ships are.
86
280120
1858
它會輸出所有船隻的位置。
04:42
Now, imagine how useful this would be to people in coast guards
87
282002
3214
想像一下,對於海上防衛隊, 這是多麼有用的資訊,
04:45
who are trying to track and stop illegal fishing.
88
285240
2736
他們的工作是要追蹤 和阻止非法捕漁。
04:48
See, legal fishing vessels
89
288000
2056
看,合法的捕漁船隻,
04:50
transmit their locations using AIS beacons.
90
290080
2936
會用 AIS 信標來傳送它們的位置。
04:53
But we frequently find ships that are not doing that.
91
293040
3616
但我們常常會發現 沒有傳送信標的船隻。
04:56
The pictures don't lie.
92
296680
1776
照片不會說謊。
04:58
And so, coast guards could use that
93
298480
1696
所以,海上防衛隊能用那資訊,
05:00
and go and find those illegal fishing vessels.
94
300200
2176
去找出非法的捕漁船隻。
05:02
And soon we'll add not just ships and planes
95
302400
2176
不只是船和飛機,之後我們很快就會把
05:04
but all the other objects,
96
304600
1296
其它物體加上去,
05:05
and we can output data feeds
97
305920
1896
我們可以把資料輸出來,
05:07
of those locations of all these objects over time
98
307840
2536
你可以針對地點、時間區段做輸出,
05:10
that can be integrated digitally from people's work flows.
99
310400
3056
這些資料就可以在大家的 工作流程中做數位整合。
05:13
In time, we could get more sophisticated browsers
100
313480
3056
到時候,我們會有更精密的瀏覽器,
05:16
that people pull in from different sources.
101
316560
2336
讓大家可以納入多重來源的資料。
05:18
But ultimately, I can imagine us abstracting out the imagery entirely
102
318920
4696
但最終,我可以想像 我們完全把影像抽取出來,
05:23
and just having a queryable interface to the Earth.
103
323640
2416
並且有一個能夠查詢地球的介面。
05:26
Imagine if we could just ask,
104
326080
1416
想像一下,若我們能問:
05:27
"Hey, how many houses are there in Pakistan?
105
327520
2536
「嘿,在巴基斯坦有多少間房子?
05:30
Give me a plot of that versus time."
106
330080
1936
把那資料搭配時間,畫張圖給我。」
05:32
"How many trees are there in the Amazon
107
332040
2176
「亞馬遜有多少棵樹?
05:34
and can you tell me the locations of the trees that have been felled
108
334240
3216
你能不能告訴我,從上週到這週之間
05:37
between this week and last week?"
109
337480
1656
哪些位置的樹木被砍伐了?」
05:39
Wouldn't that be great?
110
339160
1216
那樣不是很棒嗎?
05:40
Well, that's what we're trying to go towards,
111
340400
2136
那是我們在試圖達成的目標,
05:42
and we call it "Queryable Earth."
112
342560
1856
我們稱它為「可查詢的地球」。
05:44
So, Planet's Mission 1 was to image the whole planet every day
113
344440
3896
所以,《星球任務一號》 是要做到每天拍攝地球影像,
05:48
and make it accessible.
114
348360
2336
並讓這資訊能被大家取得。
05:50
Planet's Mission 2 is to index all the objects on the planet over time
115
350720
3816
《星球任務二號》是要將地球上 各時間點的所有物體做索引,
05:54
and make it queryable.
116
354560
1240
並供大家查詢。
05:56
Let me leave you with an analogy.
117
356760
2136
最後,我跟大家做個比喻。
05:58
Google indexed what's on the internet and made it searchable.
118
358920
3400
Google 將網路上的東西 做了索引,並供大家搜尋。
06:03
Well, we're indexing what's on the Earth and making it searchable.
119
363080
3256
我們則是將地球上的東西 做索引,並供大家搜尋。
06:06
Thank you very much.
120
366360
1336
非常謝謝各位。
06:07
(Applause)
121
367720
4520
(掌聲)
關於本網站

本網站將向您介紹對學習英語有用的 YouTube 視頻。 您將看到來自世界各地的一流教師教授的英語課程。 雙擊每個視頻頁面上顯示的英文字幕,從那裡播放視頻。 字幕與視頻播放同步滾動。 如果您有任何意見或要求,請使用此聯繫表與我們聯繫。

https://forms.gle/WvT1wiN1qDtmnspy7