Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes With Good Performance at Reduced Precision
Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes With Good Performance at Reduced Precision
复制标题
DOI：
10.1029/2020gl091363
复制
发表时间：
2020-10
影响因子：
5.2
通讯作者：
J. Yuval;P. O’Gorman;C. Hill
中科院分区：
文献类型：
--
作者：
J. Yuval;P. O’Gorman;C. Hill
改进气候模型模拟的一种有前途的方法是用数据驱动的机器学习算法取代基于简化物理模型的传统子网格参数化。然而，神经网络（NN）往往会导致不稳定性和气候漂移时，耦合到一个大气模式。在这里，我们通过粗粒化精确计算子网格项，从理想化域中的高分辨率大气模拟中学习NN参数化。NN参数化具有确保物理约束得到尊重的结构，例如通过预测次网格通量而不是趋势。NN参数化导致稳定的模拟，以与成功的随机森林参数化相似的精度复制高分辨率模拟的气候，同时需要更少的内存。我们发现，不同的水平分辨率和各种NN架构的模拟是稳定的，并大大降低数值精度的NN可以降低计算成本，而不影响模拟的质量。
A promising approach to improve climate‐model simulations is to replace traditional subgrid parameterizations based on simplified physical models by machine learning algorithms that are data‐driven. However, neural networks (NNs) often lead to instabilities and climate drift when coupled to an atmospheric model. Here, we learn an NN parameterization from a high‐resolution atmospheric simulation in an idealized domain by accurately calculating subgrid terms through coarse graining. The NN parameterization has a structure that ensures physical constraints are respected, such as by predicting subgrid fluxes instead of tendencies. The NN parameterization leads to stable simulations that replicate the climate of the high‐resolution simulation with similar accuracy to a successful random‐forest parameterization while needing far less memory. We find that the simulations are stable for different horizontal resolutions and a variety of NN architectures, and that an NN with substantially reduced numerical precision could decrease computational costs without affecting the quality of simulations.