arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.02488physics.ao-ph
收藏

全球冰-海洋模拟中用于在线海冰偏差校正的机器学习

Machine learning for online sea ice bias correction within global ice-ocean simulations

William Gregory, Mitchell Bushuk, Yongfei Zhang, Alistair Adcroft, Laure Zanna

AI总结:

本研究针对GFDL全球冰-海洋模型的海冰偏差问题,用数据增强法优化预测海冰密集度数据同化增量的CNN,改善夏季残差,方案可用于生成更优初始条件及实时海冰偏差校正。

摘要:

本研究在GFDL全球冰-海洋模型中开展在线海冰偏差校正。为此,我们使用了一项先前研究(Gregory等人,2023)开发的卷积神经网络(CNN),其用途为预测海冰密集度(SIC)数据同化(DA)增量。CNN的初步实现显示,相较于自由运行模型,SIC偏差得到系统性改善,但夏季仍存在较大误差。我们表明,通过一种数据增强方法可显著改善这些残差,该方法在训练期内对新模拟依次应用CNN和DA校正,进而生成一个新的训练数据集,用于优化初始网络的权重。我们提出,这种机器学习校正方案可用于生成更优的初始条件,也可用于季节至次季节海冰预测中的实时海冰偏差校正。

英文摘要:

In this study we perform online sea ice bias correction within a GFDL global ice-ocean model. For this, we use a convolutional neural network (CNN) which was developed in a previous study (Gregory et al., 2023) for the purpose of predicting sea ice concentration (SIC) data assimilation (DA) increments. An initial implementation of the CNN shows systematic improvements in SIC biases relative to the free-running model, however large summertime errors remain. We show that these residual errors can be significantly improved with a data augmentation approach, in which sequential CNN and DA corrections are applied to a new simulation over the training period. This then provides a new training data set with which to refine the weights of the initial network. We propose that this machine-learned correction scheme could be utilized for generating improved initial conditions, and also for real-time sea ice bias correction within seasonal-to-subseasonal sea ice forecasts.

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。

↑