Assessing Decadal Predictability in an Earth‐System Model Using Explainable Neural Networks
Assessing Decadal Predictability in an Earth‐System Model Using Explainable Neural Networks
复制标题
DOI：
10.1029/2021gl093842
复制
发表时间：
2021-06
影响因子：
5.2
通讯作者：
B. Toms;E. Barnes;J. Hurrell
中科院分区：
文献类型：
--
作者：
B. Toms;E. Barnes;J. Hurrell
我们表明，可解释的神经网络可以识别海洋变化的区域，这些区域在完全耦合的地球系统模型中对十年时间尺度的可预测性做出贡献。神经网络学习使用海面温度异常来预测未来的大陆表面温度异常。然后，我们使用一种称为分层相关传播的神经网络可解释性方法来推断哪些海洋模式会导致神经网络做出准确的预测。特别是，北大西洋和北太平洋内的区域对整个北美大陆的表面温度具有最大的可预测性。我们将所提出的方法应用于年代际变率，虽然这个概念可以推广到其他时间尺度的可预测性。此外，虽然我们的方法侧重于气候模型内部可变性的可预测模式，但也应该推广到观测数据。我们的研究有助于越来越多的证据表明，可解释的神经网络是推进地球科学知识的重要工具。
We show that explainable neural networks can identify regions of oceanic variability that contribute predictability on decadal timescales in a fully coupled Earth‐system model. The neural networks learn to use sea‐surface temperature anomalies to predict future continental surface temperature anomalies. We then use a neural‐network explainability method called layerwise relevance propagation to infer which oceanic patterns lead to accurate predictions made by the neural networks. In particular, regions within the North Atlantic Ocean and North Pacific Ocean lend the most predictability for surface temperature across continental North America. We apply the proposed methodology to decadal variability, although the concept is generalizable to other timescales of predictability. Furthermore, while our approach focuses on predictable patterns of internal variability within climate models, it should be generalizable to observational data as well. Our study contributes to the growing evidence that explainable neural networks are important tools for advancing geoscientific knowledge.