期刊
COMMUNICATIONS EARTH & ENVIRONMENT
卷 2, 期 1, 页码 -出版社
SPRINGERNATURE
DOI: 10.1038/s43247-021-00225-4
关键词
-
资金
- California Department of Water Resources Atmospheric River Program [4600010378 TO, 15 Am 22]
- California Department of Water Resources [82-19834]
- NASA
Seasonal forecasting skill in machine learning methods trained on large climate model ensembles can compete with existing dynamical models, while retaining physical interpretability. This approach overcomes the limited sample size of observational data for model training and can outperform existing dynamical models. By utilizing machine learning interpretability methods, the relevant physical processes leading to prediction skill can be identified, making this approach not a 'black box'.
Seasonal forecasting skill in machine learning methods that are trained on large climate model ensembles can compete with, or out-compete, existing dynamical models, while retaining physical interpretability. A barrier to utilizing machine learning in seasonal forecasting applications is the limited sample size of observational data for model training. To circumvent this issue, here we explore the feasibility of training various machine learning approaches on a large climate model ensemble, providing a long training set with physically consistent model realizations. After training on thousands of seasons of climate model simulations, the machine learning models are tested for producing seasonal forecasts across the historical observational period (1980-2020). For forecasting large-scale spatial patterns of precipitation across the western United States, here we show that these machine learning-based models are capable of competing with or outperforming existing dynamical models from the North American Multi Model Ensemble. We further show that this approach need not be considered a 'black box' by utilizing machine learning interpretability methods to identify the relevant physical processes that lead to prediction skill.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据