arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.09754stat.AP
收藏

由2023年夏季巨大机器学习预测产生的表面温度极值

Surface temperature extremes produced by huge machine learning hindcasts of summer 2023

Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);University of California, Berkeley(加州大学伯克利分校);The School of Environmental Sciences, University of East Anglia(东英吉利大学环境科学学院);NVIDIA(英伟达);University of California, Irvine(加州大学尔湾分校);National Energy Research Scientific Computing Center, LBNL(劳伦斯伯克利国家实验室国家能源研究科学计算中心)

Mark Risser, Ankur Mahesh, William D. Collins, Joshua North, Boris Bonev, Karthik Kashinath, Thorsten Kurth, Michael S. Pritchard, Shashank Subramanian

AI总结:

本文利用球面傅里叶神经算子机器学习模型生成7424个天气情景,研究2023年夏季极端高温事件,发现其极值温度在大部分地区不寻常,但在部分区域超出传统预测范围,凸显大规模模拟在预测湿热和干旱温度极值中的潜力。

摘要:

2023年夏季是记录中的第二热夏季,全球多地出现极端热浪。使用球面傅里叶神经算子机器学习天气模型,我们生成了7424个天气情景,模拟夏季温度极值。ML集合产生的极端热浪情景超过了再分析和数值天气预测集合的温度。我们的结果表明,ML模型的极端地表温度在大约三分之二的全球陆地面积上并不异常。然而,对于剩下的三分之一,ML生成的极端事件超出了通过极值理论外推较小集合的预测范围。此外,ML集合能够轻松生成潮湿热极值的故事模拟,这些模拟产生的公共安全警报类别比从小集合模拟的更危险。本研究突显了大规模集合模拟在改进湿热和干旱温度极值理解与预测方面的潜力。

英文摘要:

The summer of 2023 brought record-breaking heat extremes across the globe. In this work, we investigate how much worse these extremes might have become, given identical large-scale conditions. Numerical weather prediction (NWP) ensembles simulate alternate heatwave storylines, but their limited sample size diminishes their statistical coverage of observed heatwaves and ability to represent worst-case events. Using the Spherical Fourier Neural Operator machine learning (ML) weather model, we generated a huge ensemble of 7,424 storyline forecasts of summer temperature extremes. Despite being constrained by the same initial and boundary conditions and using training data from the same modeling system, the ML ensemble produced extreme heatwave scenarios exceeding temperatures from NWP ensembles. For 30% of global land areas, ML-generated extreme events were outside the prediction envelope from extrapolating smaller NWP ensembles with extreme value theory. This research demonstrates that very large ensembles substantially improve upon NWP-based characterization of worst-case heat extremes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑