这些AI设备实时守护大自然 | 胡安·M·拉维斯塔·费雷斯

选择瑞银，您将拥有一位真正全球化的合作伙伴，我们融合新技术、创新方法与意外机遇。

With UBS, you have a truly global partner incorporating new technologies, innovative approaches, and unexpected opportunities.

引领您洞见关键问题的答案，以热忱、关怀与无与伦比的专业精神交付。

Leading you to insights that help answer the questions that matter, delivered with passion, care, and unmatched expertise.

因为这关乎每日与朝阳同升，深知我们还能做得更好。

Because it's about rising with the dawn each day, knowing that we can do even better.

这就是我们理解的银行业。

That's what banking is to us.

不仅是工作，更是一门技艺。

Not just work, but a craft.

瑞银。

UBS.

银行业是我们的专精领域。

Banking is our craft.

您正在收听《TED每日谈》，我们每日为您带来激发好奇的新思想。

You're listening to TED Talks daily where we bring you new ideas to spark your curiosity every day.

我是主持人Elise Hu。

I'm your host, Elise Hu.

全球环保主义者的工作至关重要，但进展极其缓慢，远跟不上气候变化的速率。

The work of conservationists across the globe is vital, but also painstakingly slow, too slow compared to the rate of climate change.

本次演讲中，人工智能先驱Juan M.

In this talk, AI visionary Juan M.

Lavista Ferrez（微软'AI向善'实验室负责人）将介绍一项变革环保工作方式的新技术，并分享它如何极大提升我们守护地球关键生态系统的能力。

Lavista Ferrez, who leads Microsoft's AI for Good Lab, introduces a new technology that is transforming how conservationists work and shares how it can dramatically increase our ability to care for this planet's vital ecosystems.

请允许我为您介绍Andres Rojas。

Let me introduce you to Andres Rojas.

每隔几周，Andres都会深入哥伦比亚雨林徒步，穿越蚊虫滋生的沼泽与泥泞。

Every couple of weeks, Andres hikes deep in the Colombian rainforest, passing through mud and swamps of mosquitoes.

不为冒险，更不为玩乐，只为履行他的职责。

Not for adventure, definitely not for fun, but to do his job.

他需要更换相机陷阱和生物声学设备的电池与存储卡。

He needs to replace batteries and change memory cards of camera traps and bioagoustic devices.

这是当代保护科学的关键基础设施。

This is the critical infrastructure of conservation science today.

像安德烈斯这样的人是英雄，正是他们的努力将物种从灭绝边缘拯救回来。

People like Andres are heroes, and thanks to their effort, they have saved species from the brink of extinction.

全球有20万名保护工作者，他们都有一个共同点。

There are 200,000 conservationists in the world, and all of them share one thing in common.

要完成工作，他们需要数据。

To do their job, they need data.

但有趣的是，我们生活在连冰箱都能发短信提醒牛奶不足的时代。

But we live in an interesting world where we have refrigerators that can text you if you're running out of milk.

保护工作者仍需徒步数日，只为确认是否有动物经过。

Conservationists still need to hike for days just to see if an animal passed by.

当今的保护工作虽崇高必要，却进展缓慢得令人心痛。

Conservation today is heroic, is needed, but is painfully slow.

去年我在生物多样性会议上自豪地展示最新AI模型时，实则是个令人谦卑的时刻。

Last year, I was proudly presenting at a biodiversity conference some of our latest AI models, but it was in fact a very humbling moment.

因为当我向他们演示时，我意识到即便他们使用我们的模型，从设备安装到数据采集再到最终分析，整个过程的繁琐让我明白：我们的解决方案并未带来根本性改变。

Because when presenting to them, I realized that even though they were using our models, once you understood the hassle that they needed to go through, from installing these devices to collecting the data to eventually have time to analyze it, I realized that our solutions were not making such big of a difference.

我意识到，要真正产生影响，必须彻底革新生物多样性数据的工作方式。

I realized that in order for us to make a difference, we need to completely reinvent how data works in biodiversity.

这就是我们开发SPARO的原因。

This is why we developed SPARO.

SPARO全称为太阳能声学远程记录观测手表。

SPARO stands for Solar Power Acoustic Remote Recording Observation Watch.

SPARO是一个小型设备网络，作为自然中心的枢纽，连接相机陷阱、声学设备、传感器，利用太阳能处理信息，通过低功耗GPU进行边缘计算，再通过低轨道卫星回传数据。

SPARO is a small network of devices that act as a hub in the middle of nature, connecting to camera traps, acoustic devices, sensors, processing the information using solar power, processing the information on the edge using a low voltage GPU, sending results back using a low orbit satellite.

使用Sparrow，您只需一次性安装。

With Sparrow, you install it once.

您不再需要徒步收集数据。

You no longer need to hike to collect data.

您可以联网实时查看数据。

You can connect online and see the data real time.

我人生中最重要的领悟之一，就是意识到人类对复杂性上瘾。

One of my biggest lessons in life is the realization that we, as humans, are addicted to complexity.

我们喜欢复杂的项目，喜欢复杂的事物。

We like complex projects and we like complex things.

这就是为什么我们先实现登月，后给行李箱装轮子。

This is the reason we put a person on the moon before we add wheels to your luggage.

别误会我的意思。

Don't get me wrong.

如果你想让人印象深刻，解决方案可以很复杂。

If you want to impress people, your solutions can be complex.

如果你想对世界产生影响，想让人们使用你的方案，就必须保持简单。

If you want to have an impact in the world, if you want people to use your solutions, your solutions need to be simple.

构建简单的解决方案很难，但绝对值得付出努力。

Building simple solutions is hard, but it's certainly worth the effort.

这就是我们设计Sparrow时最重要的原则——保持简单。

This is why our most important principle designing Sparrow is to keep it simple.

开发简单、部署简单、组装简单。

Simple to develop, simple to deploy, simple to assemble.

Sparrow是开源的。

Sparrow is open source.

无论是生态保护科学家、研究人员还是公园管理员，任何人都能使用并改进它。

Anyone, from conservation scientists to researchers to park rangers, can use it and improve upon it.

你不是在购买一只麻雀。

You don't buy a sparrow.

你购买现成的组件，然后自己组装起来。

You buy off the shelf component and you assemble it together.

如果你有能力组装自己的宜家家具——我知道这不是人人都能做到的——那你就有能力组装一只麻雀。

If you have the ability to assemble your own IKEA furniture, and I know that's not for everybody, you're ready to assemble a sparrow.

即便看似简单，麻雀实际上功能相当强大。

Even if simple, a sparrow is actually quite powerful.

相机陷阱是四十年前发明的技术。

Camera traps is a technology that was created four decades ago.

它们装有传感器，一旦检测到动静就会拍照。

They have a sensor, and anytime that they see movement, they take a picture.

其中部分动静是由动物引起的。

Some of that movement is caused by animals.

但大多数动静是由风或其他移动物体造成的。

Majority of that movement is caused by wind or something else that moves.

这对生态保护者来说是个大麻烦，因为他们要筛选数千张照片才能获得几张目标物种的照片，耗费数百小时的时间。

This is a big hassle for conservationists, because in order for them to get just a few pictures of the species they care, they need to review thousands of pictures, costing them hundreds of hours of their time.

麻雀解决了这个问题。

Sparrow solves this problem.

通过麻雀，我们的人工智能模型能自动分类识别其中的动物。

With Sparrow, we have AI models that can automatically classify and identify the animals in them.

但麻雀的功能不止于此。

But sparrow goes further.

麻雀不仅能发现长颈鹿，还能识别出具体是哪只长颈鹿。

Sparrow not only can find a giraffe, sparrow can find that giraffe.

像长颈鹿这样的动物拥有独特的斑纹，这些独特斑纹不会随时间改变。

Animals like giraffes have a unique pattern, and that unique pattern doesn't change over time.

你可以利用这一点进行重新识别。

You can use this to re identify.

这就像指纹一样，可以用来重新识别特定的长颈鹿。

It's like a fingerprint you can use to re identify that particular giraffe.

动物重识别对保护工作至关重要，因为它能帮助了解生存状况甚至统计种群数量。

Animal re identification is critical for conservation, because it allows them to understand things like survival or even measure population.

麻雀系统可以自动完成这项工作。

Sparrow can automatically do this.

得益于与野生自然研究所的合作，这个模型如今已在麻雀系统中运行。

And thanks to our collaboration with the Wild Nature Institute, we have this model running in Sparrow today.

虽然一张图片胜过千言万语，但若只关注图像，可能会因小失大。

While a picture might be worth a thousand words, if we only focus on pictures, we might be missing the forest for the trees.

但如果你仔细聆听，故事就完全不同。

But if you listen, the story is different.

麻雀系统具备声音分离与分类功能。

Sparrow has the ability to isolate and classify sounds.

比如这里有一只青蛙。

Here, for example, there's a frog.

那是蝉鸣声。

That's a cicada.

那是金刚鹦鹉。

That's a macaw.

通过麻雀系统，我们可以借助声音测量森林的真实健康状况。

Thanks to sparrow, through sound, we can measure the true health of a forest.

从图片中识别动物并不困难。

Identifying an animal from a picture is not difficult.

通过声音识别需要非常深厚的专业知识。

Identifying from sound requires very deep expertise.

哥伦比亚Fundacion Villa de Vervosa的Paula Caixero等专家就具备这种能力。

People like Paula Caixero from Fundacion Villa de Vervosa, Colombia has this expertise.

每次考察中，她会收集长达六百小时的声音素材，然后逐小时聆听分析。

In every expedition, she collects six hundred hours' worth of sounds, and then she listens to every one of these hours.

这就像为了获取几种目标动物的样本，需要反复刷完《权力的游戏》全八季整整十遍。

This is like binge watching the whole complete eight seasons of Game of Thrones 10 times just to get a few samples of the animal she cares.

Sparrow能帮助像Paula这样的研究者。

Sparrow can help people like Paula.

Paula可以训练Sparrow专注识别特定动物或叫声，从而节省数百小时时间，让她专注于最擅长的领域——深化认知并保护心仪的物种。

Paula can train Sparrow to focus on a particular animal or a particular call so she can save hundreds of hours of her time, so she can focus on what she does best, having a better understanding and helping protect the animal she loves.

由于Sparrow联网的特性，它能够实时发送警报。

Because Sparrow is connected online, Sparrow can actually send alerts.

野火是全球性重大威胁，造成生命损失、数十亿基础设施损毁，以及重要生物多样性生态系统的彻底破坏。

Wildfires are a major global threat, costing lives, billions in infrastructure and the complete destruction of some of the most important biodiversity ecosystems.

在野火扑救中，分秒必争。

In a wildfire, every minute counts.

早期发现时，一把铁锹就能扑灭。

Detect it early, and you can stop it with a shovel.

但若延误时机，就需要推土机、灭火飞机，有时甚至需要奇迹。

But if you wait, you will need bulldozers, air tankers and sometimes a miracle.

Sparrow具备火灾早期监测能力，可向相关部门发送警报。

Sparrow has the ability to do early detection of fire and send alerts to authorities.

通过Sparrow，我们不仅能收集数据，更能据此采取行动，这些数据将助力拯救生命。

With Sparrow, we're not only collecting data, we can act on that data, and that data can help save lives.

到2025年，Sparrow将在全球各大洲投入使用。

By the 2025, we will have Sparrow running in all continents.

麻雀将彻底改变生物多样性数据的运作方式。

Sparrow will change the way biodiversity data works.

当今，保护工作的进展取决于数据流转速度。从环保人士安装设备到最终完成数据分析，目前需要耗时数月甚至一年。

Today, conservation moves at the speed of data, and when a conservationist installs a device to the time that it takes for for that data to eventually get analyzed today, it takes months, sometimes a year.

通过麻雀系统，我们致力于将耗时从数月缩短至数日。

With sparrow, we want to move from months to days.

对某些物种而言，这关键的时间差将决定其生存或灭绝的命运。

For some species, this difference, this delta can be the difference between survival and extinction.

我要把这次演讲献给那些为保护地球生物多样性奉献甚至牺牲生命的环保工作者。

I dedicate this talk to the conservationists out there who have dedicated and even sacrificed their lives to help protect biodiversity in this planet.

他们或许没有披风加身，但请务必认清——

They might not wear capes, but make absolutely no mistake.

他们就是真正的超级英雄。

They are superheroes.

然而他们需要我们的帮助。

Yet they need our help.

我们当下的工作、责任与承诺，就是为他们提供力所能及的最佳工具，让他们拥有抗争的机会。

Our job, our responsibility and our commitment today is that we will provide them with the best tools we can so they have a fighting chance.

谢谢。

Thank you.

这是胡安·M。

That was Juan M.

拉维斯塔·佩雷斯在2025年肯尼亚内罗毕TED倒计时峰会上的演讲。

Lavista Perez at the TED Countdown Summit Nairobi in Kenya in 2025.

若您对TED的选材标准感兴趣，请访问ted.com/curationguidelines了解更多。

If you're curious about TED's curation, find out more at ted.com/curationguidelines.

以上就是今天的全部内容。

And that's it for today.

TED每日演讲是TED音频联盟的一部分。

TED Talks Daily is part of the TED audio collective.

本次演讲内容经TED研究团队核实，由我们的团队——玛莎·埃斯特瓦诺斯、奥利弗·弗里德曼、布莱恩·格林、露西·利特尔和坦西卡·桑玛尼翁制作并剪辑。

This talk was fact checked by the TED research team and produced and edited by our team, Martha Estevanos, Oliver Friedman, Brian Greene, Lucy Little, and Tansika Sungmarnivong.

本期节目由克里斯托弗·费兹·博根负责混音。

This episode was mixed by Christopher Faizy Bogan.

额外支持来自艾玛·陶伯纳和丹妮拉·巴拉雷索。

Additional support from Emma Taubner and Daniella Balarezo.

我是艾莉丝·胡。

I'm Elise Hu.

明天我将带着新鲜观点回归您的订阅列表。

I'll be back tomorrow with a fresh idea for your feed.

感谢收听。

Thanks for listening.

只需一部手机和网络连接，任何人都能尝试将创作热情转化为收入。

With a phone and an Internet connection, anyone can try to turn a creative passion into income.

创意工作的价值远超人们想象。

Creative work is more valuable than people realize.

它将成为经济中极其重要的领域。

It is going to be a hugely significant area of of the economy.

但将这些创意变现究竟意味着什么？

But what does it mean to monetize all this creativity?

创作者经济。

The creator economy.

这就是下期NPR出品的TED广播时间播客主题。

That's next time on the TED Radio Hour podcast from NPR.

欢迎在您获取播客的平台订阅或收听TED广播时间。

Subscribe or listen to the TED Radio Hour wherever you get your podcasts.