在地球系统模式中模拟大气过程并利用深度学习多成员和随机参数化方案量化不确定性
Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations
AI总结：
本文面向ESM中亚网格过程表征，比较三类深度学习随机参数化方案，证明多成员方案可改善对流与热带极端降水，并通过部分耦合实现5个月稳定混合模拟。
摘要：
深度学习是表征气候模式中亚网格过程的强大工具，但迄今为止许多应用案例都采用了理想化设置和确定性方法。在这里，我们开发了具有校准不确定性量化的随机参数化方案，以学习嵌入在地球系统模式（ESM）中的超参数化（SP）的亚网格对流和湍流过程以及地表辐射通量。我们探索了三种构建随机参数化方案的方法：1）带有Monte Carlo Dropout的单个深度神经网络（DNN）；2）多成员参数化方案；以及3）带有潜空间扰动的变分编码器-解码器。我们表明，与单个DNN相比，多成员（MM）参数化方案改善了对流过程的表征，尤其是在行星边界层中。相应的不确定性量化表明，就对流过程的离散度而言，方法2）和方法3）相比基于dropout的DNN参数化方案更具优势。使用我们表现最佳的MM参数化方案进行混合模拟仍然具有挑战性，并会在最初几天内崩溃。因此，我们开发了一种务实的部分耦合策略，该策略依赖SP进行凝析物仿真。部分耦合降低了类地球混合模拟的计算效率，但使我们的MM参数化方案能够在5个月内保持模型稳定。然而，我们的混合模拟在热力学场中表现出偏差，并在降水型态上存在差异。尽管如此，与传统对流参数化方案相比，MM参数化方案能够改善对热带极端降水的再现。尽管存在这些挑战，我们的结果表明，利用不确定性量化来改善亚网格效应随机性表征的新一代MM机器学习参数化方案具有潜力。
英文摘要：
Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic parameterizations with calibrated uncertainty quantification to learn subgrid convective and turbulent processes and surface radiative fluxes of a superparameterization (SP) embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: 1) a single Deep Neural Network (DNN) with Monte Carlo Dropout; 2) a multi-member parameterization; and 3) a Variational Encoder Decoder with latent space perturbation. We show that the multi-member (MM) parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods 2) and 3) are advantageous compared to a dropout-based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best-performing MM parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the SP for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth-like simulations but enables model stability over 5 months with our MM parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the MM parameterizations enable improvements in reproducing tropical extreme precipitation compared to a traditional convection parameterization. Despite these challenges, our results indicate the potential of a new generation of MM machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects.
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。
