Gavin McCormick: Tracking the whole world's carbon emissions -- with satellites & AI | TED Countdown

翻译人员: Jason Lu 校对人员: Lexi Ding

什么造成了气候变化？

大家都知道，是人类活动 产生的温室气体的排放。

What is causing climate change?

但哪些人类活动？

I mean, it’s greenhouse gas emissions from human activities, of course.

谁在燃烧这些化石燃料？

But which human activities?

为什么燃烧，在哪里燃烧？

Who specifically is burning all of these fossil fuels,

我第一次听到这些问题时觉得奇怪，

and for what and where?

但我逐渐意识到， 即使在二十一世纪，

It sounded strange when I first heard it,

科学家对这个问题的认知也很少。

but I have come to learn that even today in the 21st century,

scientists have surprisingly little information about this question.

我是一个新联盟的一员， 其中的科学家、积极分子

和科技公司们正在 试图解决气候变化问题。

So I'm part of a new coalition of scientists, activists,

这是一个比我预期更奇怪的经历。

and actually tech companies working to address this issue.

我来详细说给你听。

It's been a stranger journey than I expected.

几十年前我们就已经知道， 排放物会上升到大气层中，

Let me break it down for you.

因为我们能看见它们在上面旋转。

So we've known for decades that emissions are rising in the atmosphere

著名的基林曲线 就是根据太空观测而来。

because we can see them swirling up around there.

So the famous Keeling Curve is based on what we can actually see from space.

但你不能轻易从太空 看到污染物的来源。

But what you can't easily see from space is how did they get there?

这个问题依旧困惑着我， 但即使在2021年，

大多数国家和经济部门，

It still boggles my mind, but even in the year 2021,

我们回答排放物 从何而来这个问题的方式，

in most countries and most sectors of the economy,

our process for actually answering where are all those emissions coming from

依旧是询问污染者 他们排放了多少。

is still to ask polluters how much they polluted.

像是寄希望于清单没有任何遗漏，

Just kind of like hope nothing is missing in that inventory

然后加起所有的数字， 有时甚至是手动写在纸上的。

and then add up all those numbers, sometimes manually, on paper.

惊人的是世界上所有国家，

都认可这样的做法。

It's amazing that every single country in the world

其中给我带来希望的，

has agreed to this process.

是所有人实际都在 帮助统计这份清单。

It's one of the great things that brings me hope

但这实在是权宜之计。

that everyone in the world is essentially contributing to this process.

如果我们真想阻止气候变化，

But it is such a stopgap solution.

这样做只能控制可测量的数据，

If we're really serious about stopping climate change,

但我们需要更多信息。

you can only manage what you can measure,

我们需要信息，

但不需要花几年时间汇编手动报告。

and we need to have more information.

We need to have information,

有些国家

not like letting it take years to compile manual reports.

在20年内没有任何排放量清单。

I mean, there are countries

你要怎么处理如此过时的信息？

that haven't had an emissions inventory in 20 years.

我们需要不仅仅只关注于

What are you actually supposed to do with information that old?

各个国家的排放量。

因为如果你想了解如何减少排放，

We need to not just be looking at what are the emissions

你需要知道：

我应该监测汽车还是工厂？

of entire countries,

because if you want to know how to reduce them,

我们国家的碳排放 主要是由什么导致的？

you need to know:

Do I need to go after cars or factories?

我们不能一直询问污染者 他们自己的排放总量。

What in my country is driving all these emissions?

还有更不易察觉的问题。

We can't keep relying on asking polluters to report how much they polluted.

比如，我经常想到

如果一家公司报告 自己减少了排放量，

And there's even more subtle problems.

Like, one that really gets me

现在我们无法证实是否真的减少了，

is if one company reports it's reduced its emissions,

we don't have a good way to know right now is that a real reduction,

有可能他们只是把这个烫手山芋

转移给了另一家公司？

should we celebrate, or did they just play hot potato

如果我们真想对付气候变化，

and sell something that pollutes to another company?

我们需要更好的工具。

我们需要找到某种方法，

If we want to get really serious about fighting climate change,

实时获取碳排放数据， 而不是花个几年时间；

we need better tools.

We need to have some way to get information

不能靠询问污染者们；

in ideally real-time, not years later;

并且能获知排放来源的具体信息，

that doesn’t rely on just asking the polluters;

而不仅仅到国家层面；

that has really detailed information about where those emissions came from,

还需要公开透明，

这样所有人都可以相信它；

not just country level;

最好还免费，

that is open and transparent,

因为不能出现

so everybody knows they can trust it;

唯独有能力支付的人 才知道排放量的情况。

and ideally, that’s free,

because we can't just have a situation

所以这是一项非常重大的 科学和工程挑战。

where only those who can afford to pay know how much is being emitted.

要如何建造一个这样的系统呢？

So that's a serious scientific and engineering challenge.

也许可以从这样一张图片开始。

How exactly would you go about building a system like that?

我们知道，这是世界上为数不多的

Well, you might want to start with a photo like this.

在烟囱中装有二氧化碳 排放监测设备的发电厂。

We know, because this is one of the few power plants in the world

这张照片被拍摄时，

that actually has a CO2 emissions sensor in its stack

它每小时排放2930吨二氧化碳。

that at the time this photo was taken,

it was emitting 2,930 tons of CO2 per hour.

但我们也知道，不久后，

这个发电厂变成了这样。

But we also know that a short time later,

当然，在那时它没有 排放任何二氧化碳。

the same exact power plant looked like this.

你单凭肉眼就可以看出来。

And at that time, of course, it was emitting zero tons of CO2.

但通常，情况会更复杂一些。

I mean, you can see that with the unaided human eye.

所以我们开始以一群 小型非政府组织的身份

But often, it's a little more complicated.

And so we have started to work as a cluster of small NGOs

开展计算机视觉AI算法训练工作，

让它观察成百上千类似这样的图片，

on training computer vision AI algorithms

从太空视角辨别发电厂

to look at hundreds of thousands of photos like this

排放一定污染物时的样子。

to recognize what a power plant looks like when it's polluting

我们能这样做是因为现在有很多免费

a certain amount of pollution from space.

和公用的卫星图片可使用。

The reason we can do this is that there are so many free

例如NASA地球资源卫星8号 和中国高分6号这样的资源。

and public satellite images available now

from sources like NASA's Landsat 8 or China's Gaofen 6.

实际上每几天就可能获取

It's possible actually to get photos every few days

世界上每个主要发电厂的照片。

of every major power plant in the entire world.

所以我运营的WattTime 和其它一些小型非政府组织

一起协作构建了一个AI算法。

And so my organization, WattTime, and a number of other small NGOs

每几天就可以扫描这样的图片，

have teamed up to build an artificial intelligence algorithm

无需询问污染者就能知道

that can scan visual imagery like this every few days

世界上每一个发电厂的排放量。

and look, without asking the polluters, to see how much they are polluting

这很令人兴奋。

for every power plant in the world.

（鼓掌）

It's pretty exciting.

(Applause)

实际还能做的更好。

因为还有其它类型的卫星。

就像电影里，我们可以 调成热红外影像，

You can actually do better than that.

Because there are other forms of satellites as well.

我们能看见发电厂是否发热。

Just like in the movies, we can switch to thermal infrared

它的重要之处体现于测试完全独立，

and we can look at whether power plants are hot as well.

使用了不同的卫星和不同的技术。

That matters because that's a completely independent assessment

所以如果两种方法结果吻合 就十分振奋人心了。

我们找到了正确的答案。

你也可以看看类似 发电厂下风区域的信息，

with different satellites and different techniques.

So if those two methods agree, that's really encouraging.

过一会儿后，

在大气层中污染物应该出现的地方， 我们是否看到了更多的排放？

We found the right answer.

You can also look at information like: Downwind from a power plant

你甚至还可以做很精细的事情，

a little while later,

do we see more emissions in the atmosphere where they ought to be?

比如可以看到发电厂旁的冷却水阀。

You can even do really subtle things,

使用来自地球的商业图像，

like you can look at the cooling water intake valve near a power plant.

我们可以看见发电厂旁边 那条河里的涟漪。

Using commercial imagery from Planet,

这表明发电厂吸入了大量水，

we are able to see ripples in a river near a power plant.

因为它的温度和污染排放量很高。

虽然没有任何一种方法是完美的，

And that means it's drawing in so much water

但当你结合许许多多不同的方法时，

because it's that hot and polluting.

So no one of these techniques is perfect,

所能达到的准确率十分出色。

but it's pretty remarkable how accurate they start to get

当我们在计算全球发电厂排放量上，

when you combine many, many different independent techniques.

开始取得不错成果时，

We got pretty excited

我们真的非常兴奋。

但了不起的艾伯特·戈尔， 鼓励我们去实现更大的梦想。

when we were starting to get pretty good results

measuring all the power plants in the world.

But then Al Gore, amazing as he is, encouraged us to dream bigger.

接受了他和Generation 公司的合作伙伴们的挑战，

我们不再局限于 探索发电厂的碳排放，

And so we got the challenge from him and the partners of Generation

而是要把范围扩大到整个人类群体，

to not just think small in terms of power plant emissions,

扩大到地球上所有主要排放来源。

but to see if we could do all human emissions

同时还要使监测方法 对所有人免费开放。

from all major sources in the planet

在他们的帮助，

and make that available and free to everyone.

和许多团队的齐心协力下，

And with their support

and with a whole lot of teaming up with other organizations,

我们成功做到了。

collectively, all of us have been able to do just that.

所以--

（鼓掌）

So --

一个非常激动人心的例子是 Transition Zero。

(Applause)

他们是位于英国的一家机构，

A really exciting example of this is Transition Zero.

能够监测钢厂的碳排放，

哪怕那些排放肉眼不可见， 他们也能监测得到。

So they're a UK-based organization

that is able to monitor the emissions of steel mills,

因为对于人工智能来说，

and they can do that even when those emissions are invisible to the naked eye.

十分重要且有趣的是，

通过卫星发出的不同种类的讯号，

Because one of the really important,

我们可以在供给链的不同部分，

interesting things about artificial intelligence

看见非常具体的化学过程。

is with different forms of signals from satellites,

你还可以监测工厂化农场。

we can look at very specific chemical processes

in different parts of the supply chain.

你知道吗，就连负责 管理它们的美国环保局，

You also have the ability to measure factory farms.

都没有完整的清单

Did you know even the United States EPA in charge of regulating them

记录美国有多少高污染工厂化农场。

does not have a complete inventory

但一家名为Synthetic的初创公司 能够采用计算机视觉

of how many highly polluting factory farms are in the United States?

列出美国高污染工厂化农场清单，

But a start-up named Synthetic has been able to apply computer vision

并且如今这份清单已经扩大到 涵盖全球的工厂化农场。

to build an inventory of them

RMI公司在监测制造和精炼过程中 石油和天然气的排放量。

and is now scaling it up to expose every factory farm worldwide.

位于印度的Blue Sky Analytics公司 在监测农作物火灾和森林火灾。

RMI is monitoring oil and gas emissions from production and refining.

Blue Sky Analytics, based in India, is monitoring crop fires and forest fires.

你说交通运输？

约翰霍普金斯大学 正在为所有地面运输建模，

You want to talk about car transportation?

并监测全球道路网。

Johns Hopkins University is modeling all the ground transportation

我们的每个组织都学会了专门监管

and looking at the road networks worldwide.

一两种特定的排放。

Each one of our organizations has learned to specialize

并在Climate TRACE 这个巨型数据库中共享数据。

in one or two forms of particular emissions.

But we’re sharing them all in a giant database known as Climate TRACE.

Climate TRACE的一个有趣之处

在于它是基于全球技术建立起来的。

One of the interesting things about Climate TRACE

这里你所看到的是Ocean Mine 对地球上所有船只做出的模型

is that it's fundamentally built on global techniques.

So here you're looking from Ocean Mine's model of every single ship on the planet

和它们相应的排放量。

这很强大因为原来

and the associated emissions.

只有富裕的国家能够非常细致地

This is really powerful because it used to be the case

监测他们的排放量。

我们现在说的是真正的全球系统，

that only rich countries can afford to look at their emissions

它对所有人免费开放。

in great detail.

我们可以成功的原因是

We are talking about properly global systems

卫星成本大幅降低。

that are available and free for everyone.

现在天空中有上千只“眼睛”，

The reason, of course, we can do this

is because satellites have come down so much in cost.

其中很多都是免费的，

信息开放给任何人使用。

There are now literally thousands of eyes in the sky up above us,

and many of them are actually free

但你知道最近几年什么东西的 成本降幅比卫星还大么？

and open to anyone to use that information.

大数据和人工智能。

But you know what's come down in recent years even more in cost than satellites?

在我们如今生活的世界，

当某个表情在推特流行,

Big data and AI.

I mean, we now live in a world

全球的自动营销算法 在几分钟内就都知道了。

where if a certain meme is trending on Twitter,

there are automated marketing algorithms that know that worldwide in minutes.

我们怀疑有的股市算法 可以在几秒内获知新信息。

这对当日交易者很有用。

We suspect there are stock market algorithms that know it in seconds;

我们整个社会实际上

it’s really useful for day traders.

将更多的资源花在了 在监测网上的猫咪搞笑视频上

So we actually exist as a society

spending more resources on monitoring funny cat video views on the internet

而非威胁整个人类文明的危机上。

（笑声）

这就显得很奇怪。

than a civilization-threatening crisis.

所以在Climate TRACE， 我们决定用极小、

(Laughter)

Something just seems strange about that.

极小一部分资源

And so at Climate TRACE, we decided to take a tiny,

和专业监控能力，

并把它们重新分配， 用于监控碳排放。

tiny fraction of those resources

and those technical monitoring capabilities

所以这是个巨型共享数据库。

and reallocate them to actually monitoring emissions.

我们的软件工程师

So it's this giant shared database.

自愿用晚上和周末的时间

I mean, we have software engineers

去做数据工程工作。

volunteering their time on nights and weekends

我们有学者来验证算法。

to make the data engineering work.

我们有非政府组织来运行不同模型。

We have academics validating algorithms.

我们有传感器和卫星 数据公司捐献代码。

We have NGOs running different models.

并且就像维基百科，

We have sensor and satellite data companies donating code.

很多不同领域专家共享的资源，

And much like Wikipedia, what's going on is all of these many,

都被放在一个所有人 都能看得到的池子里，

many different experts are sharing our resources

所有信息都被交互验证， 并且对外公开。

in a single common pot that anyone can see,

它和维基百科最大的区别，

everything has to be cross-validated, and it’s available to the public.

在于有更多实时变化。

The biggest difference from Wikipedia

那么我们为什么要做这个？

一个词，透明。

is there's a lot more real-time sensors involved.

在项目早期， 一位前气候谈判代表找到我们，

So why are we doing this?

In a word, transparency.

告诉我们巴黎协议的核心

We were approached early in the project by a former climate negotiator

应当是让国家看到

其它国家在做什么。

who told us that the heart of the Paris Agreement

他们可以学会信任彼此，

is supposed to be that countries are able to see

这样他们才会愿意 携手合作向前发展。

what everybody else is doing.

但问题在于，各国的碳排放量 都是自己报上来的，

They can learn to trust each other,

and that's why they're willing to hold hands and leap together.

并且许多国家没有资源

去做原来那种非常昂贵的监测。

But the problem is, there's a lot of self-reporting going on,

所以对于初版Climate TRACE， 我们优先考虑的是，

and a lot of countries don't have the resources

要在9月21日，第26届联合国 气候变化大会之前发布。

to do this very expensive old form of monitoring.

And so what we’ve tried to prioritize for Climate TRACE version one

初版Climate TRACE 对所有人免费开放，

is releasing before COP26, last month, September 21,

它涵盖了地球上所有国家、

a version of Climate TRACE that is free and available to everybody,

所有行业和所有年份的排放情况。

that has the emissions for every country,

比如我们现在看到的，

every sector and every year on the planet.

是马来西亚2020年 水稻生产中的排放量。

So here we're looking, for example,

这是同年澳大利亚 电力系统的排放量。

at the emissions of rice production in Malaysia in 2020.

这些都在climatetrace.org 网站上免费提供给所有人。

Or Australia's electricity emissions in the same year.

This is all available to anyone on climatetrace.org for free.

谢谢

（鼓掌）

Thank you.

(Applause)

目前它还不完美。

人工智能初期也不太好，

Now it is imperfect.

但随着时间的推移它在不断完善。

Artificial intelligence starts out not quite as good,

目前，我们已经能够比对：

我们获取的数据 与各国汇报的是否有出入。

and it gets better over time.

So far, one of the things we’ve been able to measure is:

What does this compare to what countries have been reporting?

我们不能说现在的方法毫无瑕疵，

但我们经常被问及： 国家是否应当信任彼此？

So we can't say that our methods are completely perfect yet,

此次项目中令我最震惊的是，

but one of the big questions we get is: Should countries trust each other?

And one of the most surprising things I think I've learned from this project

我想答案是肯定的。

我们肯定发现了 一些漏报的排放量，

is that I think the answer is yes.

有一些工厂肯定要被约谈。

I mean, we've definitely found some missing emissions.

但大体来说，真正震惊到我们的

There's a few industries that we need to go have some hard conversations with.

是大多数国家，

But by and large, what we've been really struck by

尽管似乎可以逍遥法外，

is the vast majority of countries

但实际却在真心诚意地和他国谈判。

appear to have been able to get away with murder,

如果你是一位前往2021年 联合国气候变化会议的谈判代表，

but negotiating with each other in complete good faith.

我想停下来，感谢这种做法，

If you're a climate negotiator heading to COP26,

因为这意味着你们相信 气候变化的未来。

I would like to just pause and appreciate what that implies for trust

但我想如果我们就此止步 对人工智能的潜力是种浪费。

所以我们的下一步： Climate TRACE第二版。

in what's about to happen.

But I think it'd be a waste of AI if we stopped there.

我们正在做的

是使地球上每个排放来源都可视化。

So our next step for Climate TRACE version two,

what we're working on,

就像这样。

is making every single emitting asset in the world visible.

这意味着它不仅可以计算国家 排放总量，还成了一种工具。

So it's going to look like this.

我和政府交谈过，他们想知道：

And what that's going to mean is not just national totals, but giving tools.

碳排放主要发生在 国家经济的哪个方面？

I’ve spoken with governments that are interested in knowing:

我和希望绿化供应链的公司交谈过，

但他们需要知道哪家工厂更干净。

Where in our economies are the emissions coming from?

I've spoken with companies who'd like to green their supply chains,

我和资产经理交谈过，

他们投入43万美元用于净零排放，

but they have to know which factories are cleaner than which other factories.

I've spoken with asset managers

但要实际达成目标， 他们需要一套管理和测量方法：

who are investing 43 trillion dollars in net-zero,

but to actually achieve their goals, they need a way to manage and measure:

这些排放量是否真的在减少？

所以激动人心的是我们现在可以确保

Are those emissions reductions really happening?

如果世界上有人希望掩盖排放量，

So I think it's pretty exciting that we can now ensure

他们可以打消这样的念头了。

那样的日子结束了。

that if anybody in the world is trying to hide emissions,

（鼓掌）

they can just forget about it.

Those days are over.

(Applause)

谢谢

但最让我激动的，

Thank you.

是在应对气候变化中给予他人工具，

But the part that really excites me the most

去更快完成这项工作。

is giving tools to others in the climate fight

谢谢

（鼓掌）

to get the job done faster.

Thank you.

(Applause)