当前位置: X-MOL 学术J. Adv. Model. Earth Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
Journal of Advances in Modeling Earth Systems ( IF 6.8 ) Pub Date : 2020-03-04 , DOI: 10.1029/2019ms001896
David John Gagne 1 , Hannah M. Christensen 1, 2 , Aneesh C. Subramanian 3 , Adam H. Monahan 4
Affiliation  

Stochastic parameterizations account for uncertainty in the representation of unresolved subgrid processes by sampling from the distribution of possible subgrid forcings. Some existing stochastic parameterizations utilize data‐driven approaches to characterize uncertainty, but these approaches require significant structural assumptions that can limit their scalability. Machine learning models, including neural networks, are able to represent a wide range of distributions and build optimized mappings between a large number of inputs and subgrid forcings. Recent research on machine learning parameterizations has focused only on deterministic parameterizations. In this study, we develop a stochastic parameterization using the generative adversarial network (GAN) machine learning framework. The GAN stochastic parameterization is trained and evaluated on output from the Lorenz '96 model, which is a common baseline model for evaluating both parameterization and data assimilation techniques. We evaluate different ways of characterizing the input noise for the model and perform model runs with the GAN parameterization at weather and climate time scales. Some of the GAN configurations perform better than a baseline bespoke parameterization at both time scales, and the networks closely reproduce the spatiotemporal correlations and regimes of the Lorenz '96 system. We also find that, in general, those models which produce skillful forecasts are also associated with the best climate simulations.

中文翻译:

随机参数化的机器学习:Lorenz '96模型中的生成对抗网络

随机参数化通过从可能的子网格强迫分布中采样来解决未解决的子网格过程表示中的不确定性。一些现有的随机参数化利用数据驱动的方法来表征不确定性,但是这些方法需要大量的结构假设,这可能会限制其可扩展性。包括神经网络在内的机器学习模型能够表示广泛的分布,并在大量输入和子网格强迫之间建立优化的映射。机器学习参数化的最新研究仅集中在确定性参数化上。在这项研究中,我们使用生成对抗网络(GAN)机器学习框架开发了随机参数化方法。GAN随机参数化训练和评估来自Lorenz '96模型的输出,该模型是用于评估参数化和数据同化技术的通用基线模型。我们评估表征模型输入噪声的不同方法,并使用GAN参数化在天气和气候时标上执行模型运行。在两个时间尺度上,某些GAN配置的性能均优于基线定制参数设置,并且网络紧密地再现了Lorenz '96系统的时空相关性和状态。我们还发现,总的来说,那些产生熟练预报的模型也与最佳的气候模拟有关。这是用于评估参数化和数据同化技术的通用基准模型。我们评估表征模型输入噪声的不同方法,并使用GAN参数化在天气和气候时标上执行模型运行。在两个时间尺度上,某些GAN配置的性能均优于基线定制参数设置,并且网络紧密地再现了Lorenz '96系统的时空相关性和状态。我们还发现,总的来说,那些产生熟练预报的模型也与最佳的气候模拟有关。这是用于评估参数化和数据同化技术的通用基准模型。我们评估表征模型输入噪声的不同方法,并使用GAN参数化在天气和气候时标上执行模型运行。在两个时间尺度上,某些GAN配置的性能均优于基线定制参数设置,并且网络紧密地再现了Lorenz '96系统的时空相关性和状态。我们还发现,总的来说,那些产生熟练预报的模型也与最佳的气候模拟有关。在两个时间尺度上,某些GAN配置的性能均优于基线定制参数设置,并且网络紧密地再现了Lorenz '96系统的时空相关性和状态。我们还发现,总的来说,那些产生熟练预报的模型也与最佳的气候模拟有关。在两个时间尺度上,某些GAN配置的性能均优于基线定制参数设置,并且网络紧密地再现了Lorenz '96系统的时空相关性和状态。我们还发现,总的来说,那些产生熟练预报的模型也与最佳的气候模拟有关。
更新日期:2020-03-04
down
wechat
bug