arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.17693physics.ao-ph
收藏

全球风暴解析模式AI模拟器中的极端事件与统计特征

Extreme events and statistics in an AI emulator of a global storm-resolving model

Allen Institute for Artificial Intelligence(艾伦人工智能研究所);NVIDIA(英伟达);NOAA/Geophysical Fluid Dynamics Laboratory(美国国家海洋和大气管理局地球物理流体动力学实验室)

Anna Kwa, W. Andre Perkins, Troy Arcomano, Noah D. Brenowitz, Christopher S. Bretherton, Spencer K. Clark, Lucas M. Harris, Jeremy McGibbon, Michael S. Pritchard, Oliver Watt-Meyer

AI总结:

本研究提出HiRO-ACEv2两阶段AI框架,模拟3公里分辨率X-SHiELD全球风暴解析模式,计算成本低300倍以上,可生成高分辨率极端事件数据,匹配极端分布尾部,跟踪热带气旋强度分布。

摘要:

我们提出HiRO-ACEv2(高分辨率输出Ai2气候模拟器),这是一个用于3公里分辨率X-SHiELD全球风暴解析模式(GSRM)AI模拟的两阶段框架,强调其生成大量数据集的能力,用于研究热带气旋和高分辨率模拟中极端事件的特征,其推理计算成本比传统数值GSRM低300倍以上。HiRO-ACEv2在仅处理降水的HiRO-ACEv1模型基础上扩展,可生成连贯的降水、10米风场和海平面气压输出,使高分辨率下能模拟更广泛的事件。通过运行100公里粗化X-SHiELD的自回归模拟器生成精细分辨率预测,其多变量输出通过单独训练的扩散模型区域降尺度至3公里分辨率。扩散降尺度步骤中,捕捉极端事件统计特征尤为重要。通过在推理时使用多个去噪器,并在训练时对数据采样、噪声采样和损失权重进行多次更新,我们在“完美预测”案例及自由运行模拟器滚动中匹配分布尾部、生成逼真极端事件的能力得到提升。HiRO-ACEv2在99.9999百分位值范围内与降水和近地面风的高分辨率参考分布高度匹配,且大致跟踪热带气旋强度的参考分布。

英文摘要:

We present HiRO-ACEv2 (High Resolution Output Ai2 Climate Emulator), a two-stage framework for AI emulation of the 3~km resolution X-SHiELD global storm-resolving model (GSRM), and highlight its ability to generate large ensembles of data for studying the characteristics of tropical cyclones and extreme events in high-resolution simulations at an inference computational cost over 300 times lower than that of traditional numerical GSRMs. HiRO-ACEv2 expands upon the precipitation-only HiRO-ACEv1 model to generate coherent precipitation, 10~m winds, and sea level pressure outputs, enabling a broader range of events to be simulated at high-resolution. Fine-resolution predictions are generated by running an autoregressive emulator of coarsened X-SHiELD at 100 km, whose multivariate outputs are regionally downscaled to 3~km resolution via a separately trained diffusion model. Particular importance is placed on capturing the statistics of extreme events during the diffusion downscaling step. Our ability to match the tails of distributions and generate realistic-looking extreme events in both the `perfect prediction' case as well as in free-running emulator rollouts is improved via the use of multiple denoisers at inference time and several updates to the data sampling, noise sampling, and loss weighting during training. HiRO-ACEv2 closely matches the high-resolution reference distributions of precipitation and near-surface winds out to their 99.9999th percentile values, and broadly tracks the reference distribution of tropical cyclone intensities.

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。

↑