A Caltech Library Service

Unsupervised Discovery of El Niño Using Causal Feature Learning on Microlevel Climate Data

Chalupka, Krzysztof and Bischoff, Tobias and Perona, Pietro and Eberhardt, Frederick (2016) Unsupervised Discovery of El Niño Using Causal Feature Learning on Microlevel Climate Data. In: Uncertainty in Artificial Intelligence. Proceedings of the Thirty-Second Conference (2016). AUAI Press , Corvallis, OR, pp. 72-81. ISBN 978-0-9966431-1-5.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We show that the climate phenomena of El Niño and La Niña arise naturally as states of macro-variables when our recent causal feature learning framework (Chalupka et al., 2015, 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 Niño or La Niña. 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 Niño. 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 et al., 2016), which circumvents the need for high-dimensional density learning.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Chalupka, Krzysztof0000-0002-1225-2112
Bischoff, Tobias0000-0003-3930-2762
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2016 AUAI Press. KC’s and PP’s work was supported by the ONR MURI grant N00014-10-1-0933 and Gordon and Betty Moore Foundation. KC’s, PP’s and FE’s work was supported by the NSF Award #1564330.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-10-1-0933
Gordon and Betty Moore FoundationUNSPECIFIED
Record Number:CaltechAUTHORS:20170530-090152140
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:77824
Deposited By: George Porter
Deposited On:30 May 2017 17:17
Last Modified:03 Oct 2019 18:02

Repository Staff Only: item control page