Oceanic Harbingers of Pacific Decadal Oscillation Predictability in CESM2 Detected by Neural Networks
Oceanic Harbingers of Pacific Decadal Oscillation Predictability in CESM2 Detected by Neural Networks
复制标题
DOI：
10.1029/2021gl095392
复制
发表时间：
2021-08
影响因子：
5.2
通讯作者：
Emily M. Gordon;E. Barnes;J. Hurrell
中科院分区：
文献类型：
--
作者：
Emily M. Gordon;E. Barnes;J. Hurrell
预测太平洋年代际振荡（PDO）的转变并理解相关机制在气候科学中已被证明是一项关键但具有挑战性的任务。作为一种年代际变率形式，PDO与大尺度气候变化和区域气候可预测性都有关联。我们表明，人工神经网络（ANNs）能够预测PDO的持续性和转变，提前期为12个月及以上。通过使用逐层相关传播来研究人工神经网络的预测，我们证明了人工神经网络利用了先前与可预测的PDO行为相关的海洋模式。对于PDO转变，人工神经网络在转变发生前12 - 27个月识别到赤道外西太平洋海洋热含量的积累。这些结果支持在气候研究中继续使用人工神经网络，其中可解释性工具可以帮助对气候系统的机制理解。
Predicting Pacific Decadal Oscillation (PDO) transitions and understanding the associated mechanisms has proven a critical but challenging task in climate science. As a form of decadal variability, the PDO is associated with both large‐scale climate shifts and regional climate predictability. We show that artificial neural networks (ANNs) predict PDO persistence and transitions with lead times of 12 months onward. Using layer‐wise relevance propagation to investigate the ANN predictions, we demonstrate that the ANNs utilize oceanic patterns that have been previously linked to predictable PDO behavior. For PDO transitions, ANNs recognize a build‐up of ocean heat content in the off‐equatorial western Pacific 12–27 months before a transition occurs. The results support the continued use of ANNs in climate studies where explainability tools can assist in mechanistic understanding of the climate system.