Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation
Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation
复制标题
DOI：
10.1029/2021ms002774
复制
发表时间：
2021-06
影响因子：
6.8
通讯作者：
Z. Martin;E. Barnes;E. Maloney
中科院分区：
文献类型：
--
作者：
Z. Martin;E. Barnes;E. Maloney
很少有研究利用机器学习技术来预测或理解马登-朱利安振荡 (MJO)，这是次季节变化和可预测性的关键来源。在这里，我们提出了一个使用浅层人工神经网络（ANN）进行实时 MJO 预测的简单框架。我们构建了两种 ANN 架构，一种是确定性的，一种是概率性的，它们使用热带变量地图来预测实时 MJO 指数。这些 ANN 可以在 10 月至 3 月的约 18 天和 4 月至 9 月的约 11 天中进行熟练的 MJO 预测，其性能优于传统的线性模型，并有效地捕获在更复杂的动态模型中发现的 MJO 可预测性的各个方面。通过改变模型输入和应用 ANN 可解释性技术来突出简单 ANN 框架的灵活性和可解释性，这些技术揭示了对 ANN 预测技能重要的来源和区域。这种简单的机器学习框架的可访问性、性能和效率更广泛地适用于预测和理解其他地球系统现象。
Few studies have utilized machine learning techniques to predict or understand the Madden‐Julian oscillation (MJO), a key source of subseasonal variability and predictability. Here, we present a simple framework for real‐time MJO prediction using shallow artificial neural networks (ANNs). We construct two ANN architectures, one deterministic and one probabilistic, that predict a real‐time MJO index using maps of tropical variables. These ANNs make skillful MJO predictions out to ∼18 days in October‐March and ∼11 days in April‐September, outperforming conventional linear models and efficiently capturing aspects of MJO predictability found in more complex, dynamical models. The flexibility and explainability of simple ANN frameworks are highlighted through varying model input and applying ANN explainability techniques that reveal sources and regions important for ANN prediction skill. The accessibility, performance, and efficiency of this simple machine learning framework is more broadly applicable to predict and understand other Earth system phenomena.