Predicting Pacific Decadal Oscillation (PDO) transitions and understanding the associated mechanisms has proven a critical but challenging task in climate science. As a form of decadal variability, the PDO is associated with both large‐scale climate shifts and regional climate predictability. We show that artificial neural networks (ANNs) predict PDO persistence and transitions with lead times of 12 months onward. Using layer‐wise relevance propagation to investigate the ANN predictions, we demonstrate that the ANNs utilize oceanic patterns that have been previously linked to predictable PDO behavior. For PDO transitions, ANNs recognize a build‐up of ocean heat content in the off‐equatorial western Pacific 12–27 months before a transition occurs. The results support the continued use of ANNs in climate studies where explainability tools can assist in mechanistic understanding of the climate system.

Artificial neural networks skillfully predict sea surface temperatures on decadal timescales in Community Earth System Model, version 2 • The networks identify predictability by assigning lower uncertainty to initial states that lead to lower prediction error • More predictable initial states coincide with combinations of phases of large scale decadal variability

Abstract. Observations from the Ozone Monitoring Instrument (OMI) on the Aura satellite are used to study the effect of energetic particle precipitation (EPP, as proxied by the geomagnetic activity index, Ap) on the Antarctic stratospheric NO2 column in late winter–spring (August–December) during the period from 2005 to 2017. We show that the polar (60–90∘ S) stratospheric NO2 column is significantly correlated with EPP throughout the Antarctic spring, until the breakdown of the polar vortex in November. The strongest correlation takes place during years with the easterly phase of the quasi-biennial oscillation (QBO). The QBO modulation may be a combination of different effects: the QBO is known to influence the amount of the primary NOx source (N2O) via transport from the Equator to the polar region; and the QBO phase also affects polar temperatures, which may provide a link to the amount of denitrification occurring in the polar vortex. We find some support for the latter in an analysis of temperature and HNO3 observations from the Microwave Limb Sounder (MLS, on Aura). Our results suggest that once the background effect of the QBO is accounted for, the NOx produced by EPP significantly contributes to the stratospheric NO2 column at the time and altitudes when the ozone hole is present in the Antarctic stratosphere. Based on our findings, and the known role of NOx as a catalyst for ozone loss, we propose that as chlorine activation continues to decrease in the Antarctic stratosphere, the total EPP-NOx needs be accounted for in predictions of Antarctic ozone recovery.

Abstract. We investigate the impact of the so-called energetic particle precipitation (EPP) indirect effect on lower stratospheric ozone, ClO, and ClONO2 in the Antarctic springtime. We use observations from the Microwave Limb Sounder (MLS) and Ozone Monitoring Instrument (OMI) on Aura, the Atmospheric Chemistry Experiment – Fourier Transform Spectrometer (ACE-FTS) on SCISAT, and the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) on Envisat, covering the period from 2005 to 2017. Using the geomagnetic activity index Ap as a proxy for EPP, we find consistent ozone increases with elevated EPP during years with an easterly phase of the quasi-biennial oscillation (QBO) in both OMI and MLS observations. While these increases are the opposite of what has previously been reported at higher altitudes, the pattern in the MLS O3 follows the typical descent patterns of EPP-NOx. The ozone enhancements are also present in the OMI total O3 column observations. Analogous to the descent patterns found in O3, we also found consistent decreases in springtime MLS ClO following winters with elevated EPP. To verify if this is due to a previously proposed mechanism involving the conversion of ClO to the reservoir species ClONO2 in reaction with NO2, we used ClONO2 observations from ACE-FTS and MIPAS. As ClO and NO2 are both catalysts in ozone destruction, the conversion to ClONO2 would result in an ozone increase. We find a positive correlation between EPP and ClONO2 in the upper stratosphere in the early spring and in the lower stratosphere in late spring, providing the first observational evidence supporting the previously proposed mechanism relating to EPP-NOx modulating Clx-driven ozone loss. Our findings suggest that EPP has played an important role in modulating ozone depletion in the last 15 years. As chlorine loading in the polar stratosphere continues to decrease in the future, this buffering mechanism will become less effective, and catalytic ozone destruction by EPP-NOx will likely become a major contributor to Antarctic ozone loss.

No abstract