arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2611.06539physics.ao-ph
收藏

评估机器学习模型对次网格涡旋动能的预测

Evaluating the prediction of subgrid eddy kinetic energy from a machine learning model

University of Reading(雷丁大学);Met Office(英国气象局)

Thomas Wilder, Ranjini Swaminathan, David Storkey, Till Kuhlbrodt

AI总结:

本研究采用卷积神经网络预测次网格涡旋动能,通过区域和特征消融实验探究机器学习涡旋闭合方案的泛化性,最佳模型的时间平均和距平$R^2$分别约为0.95和0.8-0.9。

摘要:

全球气候模型的分辨率仍过于粗糙,无法完全解析中尺度过程,因此需要次网格闭合方案来近似涡旋对解析流的反馈。随着高分辨率数据集的易得,利用机器学习开发新型涡旋闭合方案以减少模型偏差和不确定性的应用快速增长。本研究采用离线学习方法,使用卷积神经网络预测次网格涡旋动能($KE_e$),为英国地球系统模型的机器学习尺度感知GEOMETRIC涡旋闭合方案奠定初步基础。我们通过区域和特征消融实验评估多个神经网络模型,以解决“是否需要全球参数化方案或区域闭合方案已足够”的问题。当机器学习参数化模型的训练数据与未见过的区域具有相似的特征和目标分布时,模型可泛化到该区域;无法泛化的模型会出现分布偏移,或对真实涡旋动能场采用不同的滤波尺度。当保留部分特征时,可泛化的机器学习模型性能有所提升,部分特征空间在一些区域提升性能但在另一些区域降低性能。总体而言,次网格涡旋动能的功率谱密度在小尺度上往往出现偏差,不过部分特征空间可最小化该偏差。在所有区域上训练的性能最佳模型,其时间平均和距平的决定系数$R^2$分别约为0.95和0.8至0.9。

英文摘要:

Global climate model resolution is still too coarse to fully resolve mesoscale processes, therefore subgrid closures are required to approximate the feedback of eddies onto the resolved flow. With high-resolution datasets now readily available, there has been a rapid growth in the use of machine learning to develop new eddy closures that could help reduce model biases and uncertainty. In this work we employ an offline learning approach with a convolutional neural network to predict subgrid eddy kinetic energy ($KE_e$), laying the initial groundwork for a machine-learned scale-aware GEOMETRIC eddy closure for the UK's Earth System Model. We address the question of whether global parameterizations are needed or if regional closures are sufficient by evaluating a number of neural network models through region and feature ablation experiments. ML parameterization models generalize to unseen regions when their training data share similar feature and target distributions with those regions. Models that fail to generalize incur distributional shift, or employ different filtering scales for the true eddy kinetic energy field. When holding out features, there is improvement among the generalizable ML models, with some feature spaces leading to improvements in some regions but degrading performance in others. Generally, power spectral density of $KE_e$ tend to diverge at small scales, though some feature spaces are able to minimize this divergence. Overall, the best performing model trained on all regions achieves time-mean and anomaly R2 scores of R2$\approx 0.95$ and R2$\approx 0.8 - 0.9$, respectively.

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。

↑