2019年经济学人 太空人工智能技术(2)

（单词翻译）

 

Intuition-1 will view a 15km-wide swathe of Earth at a resolution of 25 metres per pixel.

Intuition-1将以每像素25米的分辨率观测15公里宽的地球带。

This will be able to reveal details such as how well crops are growing or allow the number of trees in a forest to be counted.

这将能够揭示一些细节，比如农作物生长得如何或者可以计算森林中树木的数量。

But instead of transmitting back every last bit of image data,

但这个卫星不会将图片数据的每一帧都传回来，

the satellite will summarise¹ what the user requests as useful information.

它将把用户要求的信息总结成有用的信息。

This might, for instance, be a heat-map showing areas of weeds in a field or the location of a forest fire.

例如，这可能是一份热图，显示出了田野中杂草丛生的区域或森林火灾的位置。

Reducing the data load means that some of this information can be transmitted live.

减少数据加载意味着可以现场传输其中一些信息。

The satellite will be used to prove that a hardened neural² network can survive in space.

该卫星将被用于证实经过强化的神经网络可以在太空中生存。

This could pave the way for other space applications.

这可能为其他空间应用铺平道路。

For example, the Curiosity rover on Mars was successfully upgraded in 2016

例如，2006年，火星上的好奇号火星探测车成功升级，

with a set of algorithms to detect "interesting" rocks for investigation³, instead of picking them randomly⁴.

升级后的探测车配有一套算法，可以探测到用于调查的“有趣”岩石，而非随机挑选。

A neural network could provide future rovers and deep-space probes with a better ability to make decisions.

神经网络可为未来探测车以及深空探测器提供更好的决策能力。

The neural network and hyperspectral imager have already been built and tested by KP Labs.

KP实验室已经建造并测试了神经网络和超光谱成像仪。

The kit⁵ will go into a satellite body being constructed by Clyde Space,

该设备将进入由克莱德航天公司建造的卫星体内

a satellite producer based in Scotland, and launched in 2022. After that there will be more intelligence in space.

（这是一家位于苏格兰的卫星生产公司）并于2022年发射。发射后，太空中将会有更多的智能。