20241119|人工智能有望改善气候模型（下）

In a paper published in Nature in July, Google claimed its model will soon be able to make projections over longer timescales faster, and using less power, than existing climate models.

7月份发表在《自然》杂志上的一篇论文中，谷歌声称其模型很快就能比现有的气候模型更快地、使用更少的电量对更长的时间尺度进行预测。

With additional training, the researchers also reckon Neuralgcm will be able to offer more certainty in important areas like shifts in monsoons and tropical cyclones.

研究人员还认为，通过额外的训练，Neuralgcm将能够在季风和热带气旋变化等重要领域提供更多确定性。

This optimism, say the researchers, comes from the unique abilities of machine-learning tools.

研究人员表示，这种乐观情绪来自机器学习工具的独特能力。

Where existing models sidestep intractable physics problems by using approximation, Neuralgcm's creators claim it can be guided by spotting patterns in historical data and observations.

现有模型通过使用近似值来避开棘手的物理问题，而Neuralgcm的创建者声称，它可以通过发现历史数据和观测中的模式来指导。

These claims sound impressive, but are yet to be evaluated.

这些说法听起来令人印象深刻，但尚未得到评估。

In a preprint posted online in October, a team of modellers from the Lawrence Livermore National Laboratory in California noted that Neuralgcm will remain limited until it incorporates more of the physics at play on land.

在10月份在线发布的预印本中，来自加利福尼亚州劳伦斯利弗莫尔国家实验室的建模团队指出，Neuralgcm仍将受到限制，直到它纳入更多陆地上的物理现象。

Others are more sceptical that ai methods used in short-term weather forecasting can be successfully applied to the climate.

其他人则对短期天气预报中使用的人工智能方法能否成功应用于气候持怀疑态度。

"Weather and climate are both based on physics," says Gavin Schmidt, a climate scientist who runs nasa's Goddard Institute for Space Studies, but pose different modelling challenges.

“天气和气候都是基于物理学的，”管理美国宇航局戈达德太空研究所的气候科学家加文·施密特(Gavin Schmidt)说，但这两者的建模挑战不同。

For one thing, the available data are rarely of the same quality.

首先，可用的数据很少具有相同的质量。

For weather forecasting, huge swathes of excellent data are generated every day and, therefore, able to continuously validate the previous day's predictions.

对于天气预报，每天都会产生大量优质数据，因此能够不断验证前一天的预测。

Climate models do not enjoy the same luxury. In addition, they face the challenge of simulating conditions more extreme than any previously observed, and over centuries rather than days.

气候模型则不能享受同样的奢侈。此外，它们还面临着模拟比以往任何观测到的条件都更极端的条件的挑战，而且要持续几个世纪而不是几天。

AI can nonetheless help improve climate models by addressing another major source of uncertainty: human behaviour.

尽管如此，人工智能可以通过解决另一个主要的不确定性来源来帮助改进气候模型：人类行为。

Until now, this has been overcome by codifying different social and political choices into sets of fixed scenarios which can each then be modelled.

到目前为止，这个问题已经通过将不同的社会和政治选择编纂成一组固定的场景来克服，然后可以对每个场景进行建模。

This method makes evaluations possible, but is inflexible and often vague.

这种方法使评估成为可能，但这不灵活且往往含糊不清。

With the help of ai, existing tools known as emulators can customise conventional models to suit their end users' needs.

在人工智能的帮助下，现有的被称为模拟器的工具可以定制传统模型以满足最终用户的需求。

Such emulators are now used by cities planning infrastructure projects, by insurers assessing risk and by agricultural firms estimating changes in crop yields.

如今，城市规划基础设施项目、保险公司评估风险以及农业公司估算农作物产量变化时都在使用此类模拟器。

Unlike models such as Google's Neuralgcm, which is trained on the same weather data as today's top climate models, emulators are typically trained on the outputs of full-scale climate models.

与谷歌的Neuralgcm等模型不同，这些模型使用与当今顶级气候模型相同的天气数据进行训练，而模拟器通常使用全尺寸气候模型的输出进行训练。

This allows them to piggyback on improvements to the models themselves-

这使得它们可以借助模型本身的改进——

both the new physics they are able to model and the ways in which they extrapolate beyond historical data.

既包括它们能够建模的新物理，也包括它们推断历史数据的方式。

One such emulator, developed by the Commonwealth Scientific Industrial Research Organisation in Australia in 2023, for example,

例如，澳大利亚联邦科学工业研究组织于2023年开发了一款这样的模拟器，

was capable of adjusting predictions linked to future emissions levels one million times faster than the model it was trained on.

它能够以比训练模型快一百万倍的速度调整与未来排放水平相关的预测。

Reducing the uncertainties in climate models and, perhaps more important, making them more widely available,

减少气候模型中的不确定性，或许更重要的是，让它们更广泛地普及，

will hone their usefulness for those tasked with the complex challenge of dealing with climate change.

将提高它们对那些应对气候变化这一复杂挑战的人的实用性。

And that will, hopefully, mean a better response.

希望这意味着更好的应对措施。