Exploring the Relative Importance of the MJO and ENSO to North Pacific Subseasonal Predictability

Here we explore the relative contribution of the Madden-Julian Oscillation (MJO) and El Ni & ntilde;o Southern Oscillation (ENSO) to midlatitude subseasonal predictive skill of upper atmospheric circulation over the North Pacific, using an inherently interpretable neural network applied to pre-industrial control runs of the Community Earth System Model version 2. We find that this interpretable network generally favors the state of ENSO, rather than the MJO, to make correct predictions on a range of subseasonal lead times and predictand averaging windows. Moreover, the predictability of positive circulation anomalies over the North Pacific is comparatively lower than that of their negative counterparts, especially evident when the ENSO state is important. However, when ENSO is in a neutral state, our findings indicate that the MJO provides some predictive information, particularly for positive anomalies. We identify three distinct evolutions of these MJO states, offering fresh insights into opportune forecasting windows for MJO teleconnections. Weather is hard to predict with longer forecast leads. Here, we use a data-driven statistical model to dissect tropical sources of predictability of North Pacific upper-level variability on subseasonal (2 weeks to 2 months) timescales. This model was constructed so that we can identify the relative contributions of two tropical phenomena important for predictability on these timescales. Namely, we use the Madden-Jullian Oscillation (MJO) and the El Ni & ntilde;o Southern Oscillation (ENSO) as predictor variables, two phenomena that provide a teleconnecting signal from the tropics to North Pacific variability. We find that the ENSO signal alone consistently provides more forecast predictability than the MJO. However, when ENSO is not active, the MJO provides distinct windows of forecast opportunity, particularly for anomalously anticyclonic events. We identify three evolutions of the MJO which offer new insights into forecasting weather at long forecast leads. An interpretable neural network is used to decompose contributions of MJO and ENSO to North Pacific subseasonal circulation predictability ENSO alone is overall more useful than the MJO for subseasonal predictions across various lead times and predictand averaging windows Unique MJO events, that provide enhanced subseasonal predictability during ENSO neutral conditions, are identified