Detecting climate teleconnections with Granger causality (2012.03848v2)

Abstract: Climate system teleconnections are crucial for improving climate predictability, but difficult to quantify. Standard approaches to identify teleconnections are often based on correlations between time series. Here we present a novel method leveraging Granger causality, which can infer/detect relationships between any two fields. We compare teleconnections identified by correlation and Granger causality at different timescales. We find that both Granger causality and correlation consistently recover known seasonal precipitation responses to the sea surface temperature pattern associated with the El Ni~{n}o Southern Oscillation. Such findings are robust across multiple time resolutions. In addition, we identify candidates for unexplored teleconnection responses.