Deep learning to represent subgrid processes in climate models.
Deep learning to represent subgrid processes in climate models.
复制标题
DOI：
10.1073/pnas.1810286115
复制
发表时间：
2018-09-25
影响因子：
11.1
通讯作者：
Gentine P
中科院分区：
文献类型：
--
作者：
Rasp S;Pritchard MS;Gentine P
当前的气候模型过于粗糙，无法解析大气中许多最重要的过程。传统上，这些次网格过程是在所谓的参数化中通过启发式方法近似处理的。然而，这些参数化的不完善，尤其是对于云的参数化，几十年来一直阻碍着更准确的气候预测的进展。云解析模型缓解了其粗糙同类模型的许多最严重问题，但在可预见的未来，对于气候变化预测来说，其计算要求仍然过高。在这里，我们利用深度学习来借助短期云解析模拟的力量进行气候建模。我们的数据驱动模型快速且准确，从而展示了基于机器学习的方法在气候模型开发中的潜力。
几十年来，非线性次网格过程（尤其是云）的表示一直是气候模型中不确定性的一个主要来源。云解析模型能更好地表示这些过程中的许多过程，并且现在可以在全球范围内运行，但由于计算限制，只能进行最多几年的短期模拟。在这里我们证明深度学习可以用于以极小的计算成本获取云解析建模的许多优势。我们训练一个深度神经网络，通过从一个对对流进行明确处理的多尺度模型中学习，来表示气候模型中的所有大气次网格过程。经过训练的神经网络随后在一个全球大气环流模型中取代传统的次网格参数化，在该模型中它与已解析的动力学和地表通量方案自由相互作用。多年的预测性模拟是稳定的，不仅紧密重现了云解析模拟的平均气候，还重现了变异性的关键方面，包括极端降水和赤道波谱。此外，尽管没有明确指示，神经网络也大致能保持能量守恒。最后，我们表明神经网络参数化可以推广到新的地表强迫模式，但难以应对远远超出其训练流形的温度。我们的结果表明了将深度学习用于气候模型参数化的可行性。在更广泛的背景下，我们预计数据驱动的地球系统模型开发在未来十年减少气候预测不确定性方面可以发挥关键作用。
Current climate models are too coarse to resolve many of the atmosphere’s most important processes. Traditionally, these subgrid processes are heuristically approximated in so-called parameterizations. However, imperfections in these parameterizations, especially for clouds, have impeded progress toward more accurate climate predictions for decades. Cloud-resolving models alleviate many of the gravest issues of their coarse counterparts but will remain too computationally demanding for climate change predictions for the foreseeable future. Here we use deep learning to leverage the power of short-term cloud-resolving simulations for climate modeling. Our data-driven model is fast and accurate, thereby showing the potential of machine-learning–based approaches to climate model development. The representation of nonlinear subgrid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational limitations. Here we demonstrate that deep learning can be used to capture many advantages of cloud-resolving modeling at a fraction of the computational cost. We train a deep neural network to represent all atmospheric subgrid processes in a climate model by learning from a multiscale model in which convection is treated explicitly. The trained neural network then replaces the traditional subgrid parameterizations in a global general circulation model in which it freely interacts with the resolved dynamics and the surface-flux scheme. The prognostic multiyear simulations are stable and closely reproduce not only the mean climate of the cloud-resolving simulation but also key aspects of variability, including precipitation extremes and the equatorial wave spectrum. Furthermore, the neural network approximately conserves energy despite not being explicitly instructed to. Finally, we show that the neural network parameterization generalizes to new surface forcing patterns but struggles to cope with temperatures far outside its training manifold. Our results show the feasibility of using deep learning for climate model parameterization. In a broader context, we anticipate that data-driven Earth system model development could play a key role in reducing climate prediction uncertainty in the coming decade.
登录
查看更多内容
影响因子：
6.8
作者：
Kooperman, Gabriel J.;Pritchard, Michael S.;Timmermans, Ben W.
通讯作者：
Timmermans, Ben W.
影响因子：
5.2
作者：
Gentine, P.;Pritchard, M.;Yacalis, G.
通讯作者：
Yacalis, G.
影响因子：
4.9
作者：
Collins, William D.;Rasch, Philip J.;Zhang, Minghua
通讯作者：
Zhang, Minghua
影响因子：
6.8
作者：
Arnold, Nathan P.;Randall, David A.
通讯作者：
Randall, David A.
影响因子：
4.6
作者：
Oueslati, Boutheina;Bellon, Gilles
通讯作者：
Bellon, Gilles