The goal is to learn how to write better.

分析的目的是为了提高科技英语写作水平(不是针对作者)。

Green highlight is used to indicate good writing.

绿色: 好好学习。

Yellow means "questionable."

黄色：有“问题”。

Blue calls for your attention.

蓝色：值得关注。

Anthropogenic fingerprints in daily precipitation revealed by deep learning

https://www.nature.com/articles/s41586-023-06474-x

According to twenty-first century climate-model projections, greenhouse warming willintensify rainfall variability and extremes across the globe^1,2,3,4. However, verifying this prediction using observations has remained a substantial challenge owing to large natural rainfall fluctuations at regional scales^3,4. Here we show that deep learning successfully detects the emerging climate-change signals in daily precipitation fields during the observed record. We trained a convolutional neural network (CNN)⁵ with daily precipitation fields and annual global mean surface air temperature data obtained from an ensemble of present-day and future climate-model simulations⁶. After applying the algorithm to the observational record, we found that the daily precipitation data represented an excellent predictor for the observed planetary warming, as they showed a clear deviation from natural variability since the mid-2010s. Furthermore, we analysed the deep-learning model with an explainable framework and observed that the precipitation variability of the weather timescale (period less than 10 days) over the tropical eastern Pacific and mid-latitude storm-track regions was most sensitive to anthropogenic warming. Our results highlight that, although the long-term shifts in annual mean precipitation remain indiscernible from the natural background variability, the impact of global warming on daily hydrological fluctuations has already emerged.

1)   greenhouse warming will intensify: If this is about “future” projections, one should use “would”

2)   verifying this prediction using observations has remained a substantial challenge: If observations already exist, the results are not “prediction,” but “hindcast”

3)   Here we: better using “Here, we”

4)   deep learning successfully detects: It should be “using deep learning, we … detect”

5)   daily precipitation fields during the observed record: no “s”? It should be “the period with observations”

6)   annual global mean: global-mean (as the authors use “-“ a lot); not sure “annual” is clear enough

7)   an ensemble of present-day and future climate-model simulations: I think there should be more than “one ensemble” here

8)   the daily precipitation data represented an excellent predictor: I would replace “data” with “field”

9)   planetary warming: global warming?

10)                 with an explainable framework: not sure what this means

11)                 tropical eastern Pacific: eastern tropical Pacific (vs central or western…)

Follow me, if you want to improve your writing:

如果你想提高科技英语写作能力，请跟我来...

http://blog.sciencenet.cn/blog-306792-1146690.html