Data-driven multiscale modeling of subgrid parameterizations in climate models
Data-driven multiscale modeling of subgrid parameterizations in climate models
复制标题
DOI：
10.48550/arxiv.2303.17496
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Karl Otness;L. Zanna;Joan Bruna
中科院分区：
文献类型：
--
作者：
Karl Otness;L. Zanna;Joan Bruna
子网格参数化代表在当前气候模型分辨率以下发生的物理过程，是产生准确的长期气候预测的重要组成部分。已经测试了多种方法来设计这些组件，包括深度学习方法。在这项工作中，我们评估了一个概念验证，说明了该预测问题的多尺度方法。我们训练神经网络来预测测试台模型上的子网格强制值，并检查通过使用从细到粗和从粗到细方向上的附加信息可以获得的预测精度的改进。
Subgrid parameterizations, which represent physical processes occurring below the resolution of current climate models, are an important component in producing accurate, long-term predictions for the climate. A variety of approaches have been tested to design these components, including deep learning methods. In this work, we evaluate a proof of concept illustrating a multiscale approach to this prediction problem. We train neural networks to predict subgrid forcing values on a testbed model and examine improvements in prediction accuracy that can be obtained by using additional information in both fine-to-coarse and coarse-to-fine directions.