Neural networks (NNs) are increasingly used for data-driven subgrid-scale parameterization in weather and climate models. While NNs are powerful tools for learning complex nonlinear relationships from data, there are several challenges in using them for parameterizations. Three of these challenges are 1) data imbalance related to learning rare (often large-amplitude) samples; 2) uncertainty quantification (UQ) of the predictions to provide an accuracy indicator; and 3) generalization to other climates, e.g., those with higher radiative forcing. Here, we examine the performance of methods for addressing these challenges using NN-based emulators of the Whole Atmosphere Community Climate Model (WACCM) physics-based gravity wave (GW) parameterizations as the test case. WACCM has complex, state-of-the-art parameterizations for orography-, convection- and frontal-driven GWs. Convection- and orography-driven GWs have significant data imbalance due to the absence of convection or orography in many grid points. We address data imbalance using resampling and/or weighted loss functions, enabling the successful emulation of parameterizations for all three sources. We demonstrate that three UQ methods (Bayesian NNs, variational auto-encoders, and dropouts) provide ensemble spreads that correspond to accuracy during testing, offering criteria on when a NN gives inaccurate predictions. Finally, we show that the accuracy of these NNs decreases for a warmer climate (4XCO2). However, the generalization accuracy is significantly improved by applying transfer learning, e.g., re-training only one layer using ~1% new data from the warmer climate. The findings of this study offer insights for developing reliable and generalizable data-driven parameterizations for various processes, including (but not limited) to GWs.

The variability of the Southern Hemisphere (SH) extratropical large-scale circulation is dominated by the Southern Annular Mode (SAM), whose timescale is extensively used as a key metric in evaluating state-of-the-art climate models. Past observational and theoretical studies suggest that the SAM lacks any internally generated (intrinsic) periodicity. Here, we show, using observations and a climate model hierarchy, that the SAM has an intrinsic 150-day periodicity. This periodicity is robustly detectable in the power spectra and principal oscillation patterns (aka dynamical mode decomposition) of the zonal-mean circulation, and in hemispheric-scale precipitation and ocean surface wind stress. The 150-day period is consistent with the predictions of a new reduced-order model for the SAM, which suggests that this periodicity is tied with a complex interaction of turbulent eddies and zonal wind anomalies, as the latter propagate from low to high latitudes. These findings present a rare example of periodic oscillations arising from the internal dynamics of the extratropical turbulent circulations. Based on these findings, we further propose a new metric for evaluating climate models, and show that some of the previously reported shortcomings and improvements in simulating SAM’s variability connect to the models’ ability in reproducing this periodicity. We argue that this periodicity should be considered in evaluating climate models and understanding the past, current, and projected Southern Hemisphere climate variability.

A rare record-breaking extreme rainfall event, the highest amount recorded since 1866, hit Indonesia’s capital, Jakarta, in early January 2020. The torrential rainfall was mainly caused by an active cross-equatorial northerly surge (CENS) that occurred concurrently with equatorial waves and Madden-Julian oscillation (MJO). A strong and persistent low-level northerly wind and moisture transport induced by CENS created favorable atmospheric conditions for the formation of deep convection and heavy rainfall over Jakarta. The concurrent occurrences of convectively active phases of equatorial waves (mainly Kelvin, TD-type, and eastward propagating inertia-gravity waves) and MJO during the event further supported the development of heavy rainfall by increasing low-level moisture flux convergence, whereas equatorial Rossby waves contributed indirectly to the increased moisture transport by amplifying cross-equatorial meridional flows toward Jakarta. Together, these large-scale dynamical forcing factors provided a conducive convective environment for the development of mesoscale convective systems and, hence, extreme rainfall over the region.