Question

    The terrible E1Niño strikes the globe every 2 to 7 years. As warm waters in the tropical(热带的) Pacific Ocean switch eastward and trade winds weaken the weather pattern stretches through the atmosphere, causing drought in southern Africa, wildfires in South America, and flooding on North America's Pacific coast. Climate scientists have struggled to predict El Niño events more than 1 year in advance, but artificial intelligence (AI) can now extend the latest forecasts to 18 months, according to a new study.

The new research uses a type of AI called a convolutional neural network(卷积神经网络), which is adept in recognizing images. Researchers feed the neural network a large number of training images and the AI becomes skilled at identifying fundamental patterns of those images. For example, the neural network can be trained to recognize cats in photos by identifying characteristics shared by all cats, such as hairs and four legs.

Part of the problem with earlier researches on El Niño forecasts is that they rely on a relatively small set of historical statistics for factors such as ocean temperature. To get around this shortage, the scientists fed the program re-creations of historic ocean conditions produced by a set of reliable climate models, ones frequently used for studies of climate change, says the study’s lead author, Yoo-Geun Ham, a climate scientist in South Korea. As a result, the scientists could show the computer system not just one set of actual historic data, lasting from 1871 to 1973, but several thousand reproductions of that same data by the climate models.

But it’s not clear how much real-world benefit will come from pushing forecasts beyond 1 year, cautions Stephen Zebiak, a climate scientist at Columbia University, “The kind of lead time that is actionable is probably less than a year because decision-makers are unlikely to take action further in advance,” he says.

1.What is the advantage of the latest AI forecasts?

A.Faster response. B.Higher accuracy

C.Wider application. D.Longer time range.

2.What does the underlined word “adept” probably mean?

A.Carefully-chosen. B.Well-trained.

C.Newly-developed. D.Wide-spread.

3.What is paragraph 3 mainly about?

A.Improvement on previous studies. B.Requirements for weather forecast.

C.Procedure for analyzing image data. D.Problems with early climate models.

4.What does Stephen Zebiak think of the new AI prediction?

A.It has unclear impacts. B.It calls for effective action.

C.It may not be of actual help. D.It should be treated with caution.

Answer

1.D

2.B

3.A

4.C

【解析】

这是一篇说明文。一项最新研究表明，气候科学家们一直难以提前一年多预测厄尔尼诺现象，但人工智能现在可以将最新的预测延长到18个月。文章介绍人工智能在预测厄尔尼诺现象方面的优势、对以往研究的改进和人们对此技术的看法。

1.

细节理解题。根据第一段中Climate scientists have struggled to predict El Nino events more than 1 year in advance, but artificial intelligence (Al) can now extend the latest forecasts to 18 months, according to a new study. 可知一项最新研究表明，气候科学家一直难以提前一年多预测厄尔尼诺现象，但人工智能现在可以将最新的预测延长到18个月。由此可知，最新的人工智能预测可以预测更长的时间范围。故选D。

2.

词义猜测题。根据第二段中Researchers feed the neural network a large number of training images and the Al becomes skilled at identifying fundamental patterns of those images.可知，划线处的下文提到研究人员向神经网络输入大量的训练图像，人工智能就能够熟练地识别这些图像的基本模式。即它擅长识别图像，故adept表示“熟练”之意。A. Carefully-chosen精心挑选的；B. Well-trained.熟练的。C. Newly-developed新开发的；D. Wide-spread广泛传播的。故选B。

3.

主旨大意题。根据第三段中Part of the problem with earlier researches on El Niño forecasts is that they rely on a relatively small set of historical statistics for factors such as ocean temperature.可知早期关于厄尔尼诺预测的研究存在的一个问题是，它们所依赖的海洋温度等因素的历史统计数据相对较少。结合第三段主要从新研究使用的新技术出发，引出了早期研究的部分问题，然后提出了解决这一问题的改进方法。由此可知，第三段的主要内容是对以往研究的改进。故选A。

4.

推理判断题。根据最后一段中“The kind of lead time that is actionable is probably less than a year because decision-makers are unlikely to take action further in advance,” he says.可知他说:“那种可操作的准备时间可能不到1年，因为决策者不太可能提前进一步采取行动。”由此可推知，Stephen Zebiak认为新的人工智能预测可能没有实际帮助。故选C。