Unsupervised Discovery of El Nino Using Causal Feature Learning on Microlevel Climate Data
Unsupervised Discovery of El Nino Using Causal Feature Learning on Microlevel Climate Data
复制标题
DOI：
--
复制
发表时间：
2016-05
期刊：
影响因子：
--
通讯作者：
Krzysztof Chalupka;T. Bischoff;F. Eberhardt;P. Perona
中科院分区：
文献类型：
--
作者：
Krzysztof Chalupka;T. Bischoff;F. Eberhardt;P. Perona
我们表明，当我们最近的因果特征学习框架（Chalupka 2015，Chalupka 2016）应用于太平洋赤道带上的纬向风（ZW）和海面温度（SST）的微观测量时，厄尔尼诺和拉尼娜的气候现象作为宏观变量的状态自然出现。该方法根据 ZW 和 SST 模式之间的关系来识别这些异常气候状态，而无需输入任何有关过去发生的厄尔尼诺或拉尼娜现象的信息。更简单的替代方案（i）对海表温度场进行聚类，同时忽略它们与 ZW 模式的关系，或（ii）对联合 ZW-SST 模式进行聚类，不会发现厄尔尼诺现象。我们讨论了我们的方法支持因果解释的程度，并使用低维玩具示例来解释其相对于其他聚类方法的成功。最后，我们提出了一种新的稳健且可扩展的替代方案来替代我们的原始算法（Chalupka 2016），它避免了对高维密度学习的需求。
We show that the climate phenomena of El Nino and La Nina arise naturally as states of macro-variables when our recent causal feature learning framework (Chalupka 2015, Chalupka 2016) is applied to micro-level measures of zonal wind (ZW) and sea surface temperatures (SST) taken over the equatorial band of the Pacific Ocean. The method identifies these unusual climate states on the basis of the relation between ZW and SST patterns without any input about past occurrences of El Nino or La Nina. The simpler alternatives of (i) clustering the SST fields while disregarding their relationship with ZW patterns, or (ii) clustering the joint ZW-SST patterns, do not discover El Nino. We discuss the degree to which our method supports a causal interpretation and use a low-dimensional toy example to explain its success over other clustering approaches. Finally, we propose a new robust and scalable alternative to our original algorithm (Chalupka 2016), which circumvents the need for high-dimensional density learning.