2019年经济学人 太空人工智能技术(1)（在线收听）

Speeding up the processing of space images

加快空间图像处理

Much of the information that is beamed back from space is useless.

从太空传回来的许多信息是没用的。

Pictures taken by satellites orbiting the Earth might take days to download,

由绕地球运行的卫星拍摄的照片可能需要好几天才能下载下来，

only to show lots of cloud obscuring the area of interest.

下载下来的图片只能显示大量遮盖住兴趣区的云层。

The subject matter may also be surrounded by irrelevant information. All this uses up a lot of valuable bandwidth.

主体可能也被不相关信息所围绕。所有这些都消耗了大量宝贵的带宽。

Processing data in space, before transmission, would reduce clutter, but this can be tricky.

在传输之前，在太空中处理数据可以减少杂波，但这可能会很棘手。

Cosmic rays randomly flip the ones and zeroes that computers operate on, introducing unpredictable errors.

宇宙线随机翻转电脑操作的1和0，带来不可预测的错误。

High levels of radiation can also damage electronic circuits. KP Labs, based in Gliwice, Poland,

高能级辐射也可能会破坏电子电路。位于波兰格利维策的KP实验室

is building a satellite to overcome some of these problems. Their device, called Intuition-1, is controlled by a neural network,

正在建造一个克服其中一些问题的卫星。他们的设备被称为Intuition-1，由一个神经网络进行控制，

a form of artificial intelligence modelled on the human brain.

这是一种以人脑为模型的人工智能。

The satellite is what is known in the trade as a 6U CubeSat,

这颗卫星在业内被称为6U CubeSat，

which means it is composed of six standard-sized 10x10x11.5cm modules.

这意味着它由6个标准尺寸的10x10x11.5厘米模块组成。

Intuition-1 will be equipped with a hyperspectral imager, which takes 150 pictures of every scene it looks at.

Intuition-1将装配一个超光谱成像仪，它会为每个看到的场景拍摄150张照片。

Each picture is at a different spectral frequency, so contains different information.

每张图片的光谱频率不同，所以包含信息也不同。

The neural network stitches these together using powerful graphics chips hardened against radiation.

神经网络利用强大的抗辐射图形芯片将这些数据拼接在一起。

The developers have also built error correction into their software.

开发人员还在他们的软件中内置了纠错功能。